Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 67 results for author: <span class="mathjax">Kulkarni, P</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Kulkarni%2C+P">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Kulkarni, P"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Kulkarni%2C+P&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Kulkarni, P"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Kulkarni%2C+P&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Kulkarni%2C+P&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Kulkarni%2C+P&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06344">arXiv:2411.06344</a> <span> [<a href="https://arxiv.org/pdf/2411.06344">pdf</a>, <a href="https://arxiv.org/format/2411.06344">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> CityGuessr: City-Level Video Geo-Localization on a Global Scale </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P+P">Parth Parag Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Nayak%2C+G+K">Gaurav Kumar Nayak</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+M">Mubarak Shah</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06344v1-abstract-short" style="display: inline;"> Video geolocalization is a crucial problem in current times. Given just a video, ascertaining where it was captured from can have a plethora of advantages. The problem of worldwide geolocalization has been tackled before, but only using the image modality. Its video counterpart remains relatively unexplored. Meanwhile, video geolocalization has also garnered some attention in the recent past, but… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06344v1-abstract-full').style.display = 'inline'; document.getElementById('2411.06344v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06344v1-abstract-full" style="display: none;"> Video geolocalization is a crucial problem in current times. Given just a video, ascertaining where it was captured from can have a plethora of advantages. The problem of worldwide geolocalization has been tackled before, but only using the image modality. Its video counterpart remains relatively unexplored. Meanwhile, video geolocalization has also garnered some attention in the recent past, but the existing methods are all restricted to specific regions. This motivates us to explore the problem of video geolocalization at a global scale. Hence, we propose a novel problem of worldwide video geolocalization with the objective of hierarchically predicting the correct city, state/province, country, and continent, given a video. However, no large scale video datasets that have extensive worldwide coverage exist, to train models for solving this problem. To this end, we introduce a new dataset, CityGuessr68k comprising of 68,269 videos from 166 cities all over the world. We also propose a novel baseline approach to this problem, by designing a transformer-based architecture comprising of an elegant Self-Cross Attention module for incorporating scenes as well as a TextLabel Alignment strategy for distilling knowledge from textlabels in feature space. To further enhance our location prediction, we also utilize soft-scene labels. Finally we demonstrate the performance of our method on our new dataset as well as Mapillary(MSLS). Our code and datasets are available at: https://github.com/ParthPK/CityGuessr <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06344v1-abstract-full').style.display = 'none'; document.getElementById('2411.06344v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to ECVA Eurpoean Conference on Computer Vision(ECCV) 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03487">arXiv:2410.03487</a> <span> [<a href="https://arxiv.org/pdf/2410.03487">pdf</a>, <a href="https://arxiv.org/format/2410.03487">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.53555/jes.v20i10s.6126">10.53555/jes.v20i10s.6126 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Multimodal Framework for Deepfake Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gandhi%2C+K">Kashish Gandhi</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Prutha Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Taran Shah</a>, <a href="/search/cs?searchtype=author&query=Chaudhari%2C+P">Piyush Chaudhari</a>, <a href="/search/cs?searchtype=author&query=Narvekar%2C+M">Meera Narvekar</a>, <a href="/search/cs?searchtype=author&query=Ghag%2C+K">Kranti Ghag</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.03487v1-abstract-short" style="display: inline;"> The rapid advancement of deepfake technology poses a significant threat to digital media integrity. Deepfakes, synthetic media created using AI, can convincingly alter videos and audio to misrepresent reality. This creates risks of misinformation, fraud, and severe implications for personal privacy and security. Our research addresses the critical issue of deepfakes through an innovative multimoda… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03487v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03487v1-abstract-full" style="display: none;"> The rapid advancement of deepfake technology poses a significant threat to digital media integrity. Deepfakes, synthetic media created using AI, can convincingly alter videos and audio to misrepresent reality. This creates risks of misinformation, fraud, and severe implications for personal privacy and security. Our research addresses the critical issue of deepfakes through an innovative multimodal approach, targeting both visual and auditory elements. This comprehensive strategy recognizes that human perception integrates multiple sensory inputs, particularly visual and auditory information, to form a complete understanding of media content. For visual analysis, a model that employs advanced feature extraction techniques was developed, extracting nine distinct facial characteristics and then applying various machine learning and deep learning models. For auditory analysis, our model leverages mel-spectrogram analysis for feature extraction and then applies various machine learning and deep learningmodels. To achieve a combined analysis, real and deepfake audio in the original dataset were swapped for testing purposes and ensured balanced samples. Using our proposed models for video and audio classification i.e. Artificial Neural Network and VGG19, the overall sample is classified as deepfake if either component is identified as such. Our multimodal framework combines visual and auditory analyses, yielding an accuracy of 94%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03487v1-abstract-full').style.display = 'none'; document.getElementById('2410.03487v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 pages, 14 figures, Accepted in Journal of Electrical Systems</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17777">arXiv:2409.17777</a> <span> [<a href="https://arxiv.org/pdf/2409.17777">pdf</a>, <a href="https://arxiv.org/format/2409.17777">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+R">Raja Kumar</a>, <a href="/search/cs?searchtype=author&query=Singhal%2C+R">Raghav Singhal</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranamya Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+D">Deval Mehta</a>, <a href="/search/cs?searchtype=author&query=Jadhav%2C+K">Kshitij Jadhav</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17777v2-abstract-short" style="display: inline;"> Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple pairwise associations. We propose M3CoL, a Multimodal Mixup Contrastive Learning approach to capture nuanced shared relations inherent in multimodal data. Our key contribution is a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17777v2-abstract-full').style.display = 'inline'; document.getElementById('2409.17777v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17777v2-abstract-full" style="display: none;"> Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple pairwise associations. We propose M3CoL, a Multimodal Mixup Contrastive Learning approach to capture nuanced shared relations inherent in multimodal data. Our key contribution is a Mixup-based contrastive loss that learns robust representations by aligning mixed samples from one modality with their corresponding samples from other modalities thereby capturing shared relations between them. For multimodal classification tasks, we introduce a framework that integrates a fusion module with unimodal prediction modules for auxiliary supervision during training, complemented by our proposed Mixup-based contrastive loss. Through extensive experiments on diverse datasets (N24News, ROSMAP, BRCA, and Food-101), we demonstrate that M3CoL effectively captures shared multimodal relations and generalizes across domains. It outperforms state-of-the-art methods on N24News, ROSMAP, and BRCA, while achieving comparable performance on Food-101. Our work highlights the significance of learning shared relations for robust multimodal learning, opening up promising avenues for future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17777v2-abstract-full').style.display = 'none'; document.getElementById('2409.17777v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">RK and RS contributed equally to this work, 20 Pages, 8 Figures, 9 Tables. Another version of the paper accepted at NeurIPS 2024 Workshop on Unifying Representations in Neural Models (UniReps)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13704">arXiv:2408.13704</a> <span> [<a href="https://arxiv.org/pdf/2408.13704">pdf</a>, <a href="https://arxiv.org/format/2408.13704">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> DHP Benchmark: Are LLMs Good NLG Evaluators? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yicheng Wang</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+J">Jiayi Yuan</a>, <a href="/search/cs?searchtype=author&query=Chuang%2C+Y">Yu-Neng Chuang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhuoer Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yingchi Liu</a>, <a href="/search/cs?searchtype=author&query=Cusick%2C+M">Mark Cusick</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Param Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+Z">Zhengping Ji</a>, <a href="/search/cs?searchtype=author&query=Ibrahim%2C+Y">Yasser Ibrahim</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xia Hu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.13704v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks. However, the capabilities of LLMs in scoring NLG quality remain inadequately explored. Current studies depend on human assessments and simple metrics that fail to capture the discernment of LLMs across diverse NLG tasks. To address this gap, we propose the Discernment of Hierarchical Per… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13704v1-abstract-full').style.display = 'inline'; document.getElementById('2408.13704v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13704v1-abstract-full" style="display: none;"> Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks. However, the capabilities of LLMs in scoring NLG quality remain inadequately explored. Current studies depend on human assessments and simple metrics that fail to capture the discernment of LLMs across diverse NLG tasks. To address this gap, we propose the Discernment of Hierarchical Perturbation (DHP) benchmarking framework, which provides quantitative discernment scores for LLMs utilizing hierarchically perturbed text data and statistical tests to measure the NLG evaluation capabilities of LLMs systematically. We have re-established six evaluation datasets for this benchmark, covering four NLG tasks: Summarization, Story Completion, Question Answering, and Translation. Our comprehensive benchmarking of five major LLM series provides critical insight into their strengths and limitations as NLG evaluators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13704v1-abstract-full').style.display = 'none'; document.getElementById('2408.13704v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.02140">arXiv:2408.02140</a> <span> [<a href="https://arxiv.org/pdf/2408.02140">pdf</a>, <a href="https://arxiv.org/format/2408.02140">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+S+S">Somnath Sendhil Kumar</a>, <a href="/search/cs?searchtype=author&query=Govindarajulu%2C+Y">Yuvaraj Govindarajulu</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pavan Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Manojkumar Parmar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.02140v1-abstract-short" style="display: inline;"> In the domain of black-box model extraction, conventional methods reliant on soft labels or surrogate datasets struggle with scaling to high-dimensional input spaces and managing the complexity of an extensive array of interrelated classes. In this work, we present a novel approach that utilizes SHAP (SHapley Additive exPlanations) to enhance synthetic data generation. SHAP quantifies the individu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02140v1-abstract-full').style.display = 'inline'; document.getElementById('2408.02140v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.02140v1-abstract-full" style="display: none;"> In the domain of black-box model extraction, conventional methods reliant on soft labels or surrogate datasets struggle with scaling to high-dimensional input spaces and managing the complexity of an extensive array of interrelated classes. In this work, we present a novel approach that utilizes SHAP (SHapley Additive exPlanations) to enhance synthetic data generation. SHAP quantifies the individual contributions of each input feature towards the victim model's output, facilitating the optimization of an energy-based GAN towards a desirable output. This method significantly boosts performance, achieving a 16.45% increase in the accuracy of image classification models and extending to video classification models with an average improvement of 26.11% and a maximum of 33.36% on challenging datasets such as UCF11, UCF101, Kinetics 400, Kinetics 600, and Something-Something V2. We further demonstrate the effectiveness and practical utility of our method under various scenarios, including the availability of top-k prediction probabilities, top-k prediction labels, and top-1 labels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02140v1-abstract-full').style.display = 'none'; document.getElementById('2408.02140v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.14030">arXiv:2407.14030</a> <span> [<a href="https://arxiv.org/pdf/2407.14030">pdf</a>, <a href="https://arxiv.org/format/2407.14030">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> HeCiX: Integrating Knowledge Graphs and Large Language Models for Biomedical Research </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P+S">Prerana Sanjay Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+M">Muskaan Jain</a>, <a href="/search/cs?searchtype=author&query=Sheshanarayana%2C+D">Disha Sheshanarayana</a>, <a href="/search/cs?searchtype=author&query=Parthiban%2C+S">Srinivasan Parthiban</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.14030v1-abstract-short" style="display: inline;"> Despite advancements in drug development strategies, 90% of clinical trials fail. This suggests overlooked aspects in target validation and drug optimization. In order to address this, we introduce HeCiX-KG, Hetionet-Clinicaltrials neXus Knowledge Graph, a novel fusion of data from ClinicalTrials.gov and Hetionet in a single knowledge graph. HeCiX-KG combines data on previously conducted clinical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14030v1-abstract-full').style.display = 'inline'; document.getElementById('2407.14030v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.14030v1-abstract-full" style="display: none;"> Despite advancements in drug development strategies, 90% of clinical trials fail. This suggests overlooked aspects in target validation and drug optimization. In order to address this, we introduce HeCiX-KG, Hetionet-Clinicaltrials neXus Knowledge Graph, a novel fusion of data from ClinicalTrials.gov and Hetionet in a single knowledge graph. HeCiX-KG combines data on previously conducted clinical trials from ClinicalTrials.gov, and domain expertise on diseases and genes from Hetionet. This offers a thorough resource for clinical researchers. Further, we introduce HeCiX, a system that uses LangChain to integrate HeCiX-KG with GPT-4, and increase its usability. HeCiX shows high performance during evaluation against a range of clinically relevant issues, proving this model to be promising for enhancing the effectiveness of clinical research. Thus, this approach provides a more holistic view of clinical trials and existing biological data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14030v1-abstract-full').style.display = 'none'; document.getElementById('2407.14030v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 3 figures, under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.11599">arXiv:2407.11599</a> <span> [<a href="https://arxiv.org/pdf/2407.11599">pdf</a>, <a href="https://arxiv.org/format/2407.11599">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Enhancing TinyML Security: Study of Adversarial Attack Transferability </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+P">Parin Shah</a>, <a href="/search/cs?searchtype=author&query=Govindarajulu%2C+Y">Yuvaraj Govindarajulu</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pavan Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Manojkumar Parmar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.11599v2-abstract-short" style="display: inline;"> The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence on cloud connections. While TinyML offers real-time data analysis and swift responses critical for diverse applications, its devices' intrinsic resource limitations expose them to security risks. This research delves into… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11599v2-abstract-full').style.display = 'inline'; document.getElementById('2407.11599v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.11599v2-abstract-full" style="display: none;"> The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence on cloud connections. While TinyML offers real-time data analysis and swift responses critical for diverse applications, its devices' intrinsic resource limitations expose them to security risks. This research delves into the adversarial vulnerabilities of AI models on resource-constrained embedded hardware, with a focus on Model Extraction and Evasion Attacks. Our findings reveal that adversarial attacks from powerful host machines could be transferred to smaller, less secure devices like ESP32 and Raspberry Pi. This illustrates that adversarial attacks could be extended to tiny devices, underscoring vulnerabilities, and emphasizing the necessity for reinforced security measures in TinyML deployments. This exploration enhances the comprehension of security challenges in TinyML and offers insights for safeguarding sensitive data and ensuring device dependability in AI-powered edge computing settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11599v2-abstract-full').style.display = 'none'; document.getElementById('2407.11599v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted and presented at tinyML Foundation EMEA Innovation Forum 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.16932">arXiv:2406.16932</a> <span> [<a href="https://arxiv.org/pdf/2406.16932">pdf</a>, <a href="https://arxiv.org/format/2406.16932">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.17023/pn92-d609">10.17023/pn92-d609 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Xi-Net: Transformer Based Seismic Waveform Reconstructor </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gaharwar%2C+A">Anshuman Gaharwar</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P+P">Parth Parag Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Dickey%2C+J">Joshua Dickey</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+M">Mubarak Shah</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.16932v1-abstract-short" style="display: inline;"> Missing/erroneous data is a major problem in today's world. Collected seismic data sometimes contain gaps due to multitude of reasons like interference and sensor malfunction. Gaps in seismic waveforms hamper further signal processing to gain valuable information. Plethora of techniques are used for data reconstruction in other domains like image, video, audio, but translation of those methods to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16932v1-abstract-full').style.display = 'inline'; document.getElementById('2406.16932v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.16932v1-abstract-full" style="display: none;"> Missing/erroneous data is a major problem in today's world. Collected seismic data sometimes contain gaps due to multitude of reasons like interference and sensor malfunction. Gaps in seismic waveforms hamper further signal processing to gain valuable information. Plethora of techniques are used for data reconstruction in other domains like image, video, audio, but translation of those methods to address seismic waveforms demands adapting them to lengthy sequence inputs, which is practically complex. Even if that is accomplished, high computational costs and inefficiency would still persist in these predominantly convolution-based reconstruction models. In this paper, we present a transformer-based deep learning model, Xi-Net, which utilizes multi-faceted time and frequency domain inputs for accurate waveform reconstruction. Xi-Net converts the input waveform to frequency domain, employs separate encoders for time and frequency domains, and one decoder for getting reconstructed output waveform from the fused features. 1D shifted-window transformer blocks form the elementary units of all parts of the model. To the best of our knowledge, this is the first transformer-based deep learning model for seismic waveform reconstruction. We demonstrate this model's prowess by filling 0.5-1s random gaps in 120s waveforms, resembling the original waveform quite closely. The code, models can be found at: https://github.com/Anshuman04/waveformReconstructor. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16932v1-abstract-full').style.display = 'none'; document.getElementById('2406.16932v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Oral Presentation at IEEE International Conference on Image Processing(ICIP) 2023 (Multidimensional Signal Processing Track)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.00156">arXiv:2405.00156</a> <span> [<a href="https://arxiv.org/pdf/2405.00156">pdf</a>, <a href="https://arxiv.org/format/2405.00156">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> </div> </div> <p class="title is-5 mathjax"> Expanding the Horizon: Enabling Hybrid Quantum Transfer Learning for Long-Tailed Chest X-Ray Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chan%2C+S">Skylar Chan</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.00156v2-abstract-short" style="display: inline;"> Quantum machine learning (QML) has the potential for improving the multi-label classification of rare, albeit critical, diseases in large-scale chest x-ray (CXR) datasets due to theoretical quantum advantages over classical machine learning (CML) in sample efficiency and generalizability. While prior literature has explored QML with CXRs, it has focused on binary classification tasks with small da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.00156v2-abstract-full').style.display = 'inline'; document.getElementById('2405.00156v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.00156v2-abstract-full" style="display: none;"> Quantum machine learning (QML) has the potential for improving the multi-label classification of rare, albeit critical, diseases in large-scale chest x-ray (CXR) datasets due to theoretical quantum advantages over classical machine learning (CML) in sample efficiency and generalizability. While prior literature has explored QML with CXRs, it has focused on binary classification tasks with small datasets due to limited access to quantum hardware and computationally expensive simulations. To that end, we implemented a Jax-based framework that enables the simulation of medium-sized qubit architectures with significant improvements in wall-clock time over current software offerings. We evaluated the performance of our Jax-based framework in terms of efficiency and performance for hybrid quantum transfer learning for long-tailed classification across 8, 14, and 19 disease labels using large-scale CXR datasets. The Jax-based framework resulted in up to a 58% and 95% speed-up compared to PyTorch and TensorFlow implementations, respectively. However, compared to CML, QML demonstrated slower convergence and an average AUROC of 0.70, 0.73, and 0.74 for the classification of 8, 14, and 19 CXR disease labels. In comparison, the CML models had an average AUROC of 0.77, 0.78, and 0.80 respectively. In conclusion, our work presents an accessible implementation of hybrid quantum transfer learning for long-tailed CXR classification with a computationally efficient Jax-based framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.00156v2-abstract-full').style.display = 'none'; document.getElementById('2405.00156v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 13 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.15656">arXiv:2404.15656</a> <span> [<a href="https://arxiv.org/pdf/2404.15656">pdf</a>, <a href="https://arxiv.org/format/2404.15656">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khazanchi%2C+V">Vidit Khazanchi</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pavan Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Govindarajulu%2C+Y">Yuvaraj Govindarajulu</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Manojkumar Parmar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.15656v2-abstract-short" style="display: inline;"> Emerging vulnerabilities in machine learning (ML) models due to adversarial attacks raise concerns about their reliability. Specifically, evasion attacks manipulate models by introducing precise perturbations to input data, causing erroneous predictions. To address this, we propose a methodology combining SHapley Additive exPlanations (SHAP) for feature importance analysis with an innovative Optim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15656v2-abstract-full').style.display = 'inline'; document.getElementById('2404.15656v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.15656v2-abstract-full" style="display: none;"> Emerging vulnerabilities in machine learning (ML) models due to adversarial attacks raise concerns about their reliability. Specifically, evasion attacks manipulate models by introducing precise perturbations to input data, causing erroneous predictions. To address this, we propose a methodology combining SHapley Additive exPlanations (SHAP) for feature importance analysis with an innovative Optimal Epsilon technique for conducting evasion attacks. Our approach begins with SHAP-based analysis to understand model vulnerabilities, crucial for devising targeted evasion strategies. The Optimal Epsilon technique, employing a Binary Search algorithm, efficiently determines the minimum epsilon needed for successful evasion. Evaluation across diverse machine learning architectures demonstrates the technique's precision in generating adversarial samples, underscoring its efficacy in manipulating model outcomes. This study emphasizes the critical importance of continuous assessment and monitoring to identify and mitigate potential security risks in machine learning systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15656v2-abstract-full').style.display = 'none'; document.getElementById('2404.15656v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.08311">arXiv:2404.08311</a> <span> [<a href="https://arxiv.org/pdf/2404.08311">pdf</a>, <a href="https://arxiv.org/format/2404.08311">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> emucxl: an emulation framework for CXL-based disaggregated memory applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gond%2C+R">Raja Gond</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Purushottam Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.08311v1-abstract-short" style="display: inline;"> The emergence of CXL (Compute Express Link) promises to transform the status of interconnects between host and devices and in turn impact the design of all software layers. With its low overhead, low latency, and memory coherency capabilities, CXL has the potential to improve the performance of existing devices while making viable new operational use cases (e.g., disaggregated memory pools, cache… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08311v1-abstract-full').style.display = 'inline'; document.getElementById('2404.08311v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.08311v1-abstract-full" style="display: none;"> The emergence of CXL (Compute Express Link) promises to transform the status of interconnects between host and devices and in turn impact the design of all software layers. With its low overhead, low latency, and memory coherency capabilities, CXL has the potential to improve the performance of existing devices while making viable new operational use cases (e.g., disaggregated memory pools, cache coherent memory across devices etc.). The focus of this work is design of applications and middleware with use of CXL for supporting disaggregated memory. A vital building block for solutions in this space is the availability of a standard CXL hardware and software platform. Currently, CXL devices are not commercially available, and researchers often rely on custom-built hardware or emulation techniques and/or use customized software interfaces and abstractions. These techniques do not provide a standard usage model and abstraction layer for CXL usage, and developers and researchers have to reinvent the CXL setup to design and test their solutions, our work aims to provide a standardized view of the CXL emulation platform and the software interfaces and abstractions for disaggregated memory. This standardization is designed and implemented as a user space library, emucxl and is available as a virtual appliance. The library provides a user space API and is coupled with a NUMA-based CXL emulation backend. Further, we demonstrate usage of the standardized API for different use cases relying on disaggregated memory and show that generalized functionality can be built using the open source emucxl library. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08311v1-abstract-full').style.display = 'none'; document.getElementById('2404.08311v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.07374">arXiv:2404.07374</a> <span> [<a href="https://arxiv.org/pdf/2404.07374">pdf</a>, <a href="https://arxiv.org/format/2404.07374">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Improving Multi-Center Generalizability of GAN-Based Fat Suppression using Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Kukreja%2C+H">Harshita Kukreja</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+V">Vivian Zhang</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.07374v1-abstract-short" style="display: inline;"> Generative Adversarial Network (GAN)-based synthesis of fat suppressed (FS) MRIs from non-FS proton density sequences has the potential to accelerate acquisition of knee MRIs. However, GANs trained on single-site data have poor generalizability to external data. We show that federated learning can improve multi-center generalizability of GANs for synthesizing FS MRIs, while facilitating privacy-pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07374v1-abstract-full').style.display = 'inline'; document.getElementById('2404.07374v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07374v1-abstract-full" style="display: none;"> Generative Adversarial Network (GAN)-based synthesis of fat suppressed (FS) MRIs from non-FS proton density sequences has the potential to accelerate acquisition of knee MRIs. However, GANs trained on single-site data have poor generalizability to external data. We show that federated learning can improve multi-center generalizability of GANs for synthesizing FS MRIs, while facilitating privacy-preserving multi-institutional collaborations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07374v1-abstract-full').style.display = 'none'; document.getElementById('2404.07374v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.20147">arXiv:2403.20147</a> <span> [<a href="https://arxiv.org/pdf/2403.20147">pdf</a>, <a href="https://arxiv.org/format/2403.20147">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sahoo%2C+N+R">Nihar Ranjan Sahoo</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P+P">Pranamya Prashant Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Asad%2C+N">Narjis Asad</a>, <a href="/search/cs?searchtype=author&query=Ahmad%2C+A">Arif Ahmad</a>, <a href="/search/cs?searchtype=author&query=Goyal%2C+T">Tanu Goyal</a>, <a href="/search/cs?searchtype=author&query=Garimella%2C+A">Aparna Garimella</a>, <a href="/search/cs?searchtype=author&query=Bhattacharyya%2C+P">Pushpak Bhattacharyya</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.20147v2-abstract-short" style="display: inline;"> The pervasive influence of social biases in language data has sparked the need for benchmark datasets that capture and evaluate these biases in Large Language Models (LLMs). Existing efforts predominantly focus on English language and the Western context, leaving a void for a reliable dataset that encapsulates India's unique socio-cultural nuances. To bridge this gap, we introduce IndiBias, a comp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.20147v2-abstract-full').style.display = 'inline'; document.getElementById('2403.20147v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.20147v2-abstract-full" style="display: none;"> The pervasive influence of social biases in language data has sparked the need for benchmark datasets that capture and evaluate these biases in Large Language Models (LLMs). Existing efforts predominantly focus on English language and the Western context, leaving a void for a reliable dataset that encapsulates India's unique socio-cultural nuances. To bridge this gap, we introduce IndiBias, a comprehensive benchmarking dataset designed specifically for evaluating social biases in the Indian context. We filter and translate the existing CrowS-Pairs dataset to create a benchmark dataset suited to the Indian context in Hindi language. Additionally, we leverage LLMs including ChatGPT and InstructGPT to augment our dataset with diverse societal biases and stereotypes prevalent in India. The included bias dimensions encompass gender, religion, caste, age, region, physical appearance, and occupation. We also build a resource to address intersectional biases along three intersectional dimensions. Our dataset contains 800 sentence pairs and 300 tuples for bias measurement across different demographics. The dataset is available in English and Hindi, providing a size comparable to existing benchmark datasets. Furthermore, using IndiBias we compare ten different language models on multiple bias measurement metrics. We observed that the language models exhibit more bias across a majority of the intersectional groups. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.20147v2-abstract-full').style.display = 'none'; document.getElementById('2403.20147v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.15218">arXiv:2403.15218</a> <span> [<a href="https://arxiv.org/pdf/2403.15218">pdf</a>, <a href="https://arxiv.org/format/2403.15218">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Anytime, Anywhere, Anyone: Investigating the Feasibility of Segment Anything Model for Crowd-Sourcing Medical Image Annotations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Savani%2C+D">Dharmam Savani</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+A">Andrew Chan</a>, <a href="/search/cs?searchtype=author&query=Chatterjee%2C+D">Devina Chatterjee</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.15218v1-abstract-short" style="display: inline;"> Curating annotations for medical image segmentation is a labor-intensive and time-consuming task that requires domain expertise, resulting in "narrowly" focused deep learning (DL) models with limited translational utility. Recently, foundation models like the Segment Anything Model (SAM) have revolutionized semantic segmentation with exceptional zero-shot generalizability across various domains, i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15218v1-abstract-full').style.display = 'inline'; document.getElementById('2403.15218v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.15218v1-abstract-full" style="display: none;"> Curating annotations for medical image segmentation is a labor-intensive and time-consuming task that requires domain expertise, resulting in "narrowly" focused deep learning (DL) models with limited translational utility. Recently, foundation models like the Segment Anything Model (SAM) have revolutionized semantic segmentation with exceptional zero-shot generalizability across various domains, including medical imaging, and hold a lot of promise for streamlining the annotation process. However, SAM has yet to be evaluated in a crowd-sourced setting to curate annotations for training 3D DL segmentation models. In this work, we explore the potential of SAM for crowd-sourcing "sparse" annotations from non-experts to generate "dense" segmentation masks for training 3D nnU-Net models, a state-of-the-art DL segmentation model. Our results indicate that while SAM-generated annotations exhibit high mean Dice scores compared to ground-truth annotations, nnU-Net models trained on SAM-generated annotations perform significantly worse than nnU-Net models trained on ground-truth annotations ($p<0.001$, all). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15218v1-abstract-full').style.display = 'none'; document.getElementById('2403.15218v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.05713">arXiv:2402.05713</a> <span> [<a href="https://arxiv.org/pdf/2402.05713">pdf</a>, <a href="https://arxiv.org/format/2402.05713">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Hidden in Plain Sight: Undetectable Adversarial Bias Attacks on Vulnerable Patient Populations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+A">Andrew Chan</a>, <a href="/search/cs?searchtype=author&query=Navarathna%2C+N">Nithya Navarathna</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+S">Skylar Chan</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.05713v3-abstract-short" style="display: inline;"> The proliferation of artificial intelligence (AI) in radiology has shed light on the risk of deep learning (DL) models exacerbating clinical biases towards vulnerable patient populations. While prior literature has focused on quantifying biases exhibited by trained DL models, demographically targeted adversarial bias attacks on DL models and its implication in the clinical environment remains an u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05713v3-abstract-full').style.display = 'inline'; document.getElementById('2402.05713v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.05713v3-abstract-full" style="display: none;"> The proliferation of artificial intelligence (AI) in radiology has shed light on the risk of deep learning (DL) models exacerbating clinical biases towards vulnerable patient populations. While prior literature has focused on quantifying biases exhibited by trained DL models, demographically targeted adversarial bias attacks on DL models and its implication in the clinical environment remains an underexplored field of research in medical imaging. In this work, we demonstrate that demographically targeted label poisoning attacks can introduce undetectable underdiagnosis bias in DL models. Our results across multiple performance metrics and demographic groups like sex, age, and their intersectional subgroups show that adversarial bias attacks demonstrate high-selectivity for bias in the targeted group by degrading group model performance without impacting overall model performance. Furthermore, our results indicate that adversarial bias attacks result in biased DL models that propagate prediction bias even when evaluated with external datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05713v3-abstract-full').style.display = 'none'; document.getElementById('2402.05713v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">29 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.07148">arXiv:2401.07148</a> <span> [<a href="https://arxiv.org/pdf/2401.07148">pdf</a>, <a href="https://arxiv.org/format/2401.07148">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Assessing the Effectiveness of Binary-Level CFI Techniques </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vaidya%2C+R+K">Ruturaj K. Vaidya</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P+A">Prasad A. Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.07148v1-abstract-short" style="display: inline;"> Memory corruption is an important class of vulnerability that can be leveraged to craft control flow hijacking attacks. Control Flow Integrity (CFI) provides protection against such attacks. Application of type-based CFI policies requires information regarding the number and type of function arguments. Binary-level type recovery is inherently speculative, which motivates the need for an evaluation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.07148v1-abstract-full').style.display = 'inline'; document.getElementById('2401.07148v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.07148v1-abstract-full" style="display: none;"> Memory corruption is an important class of vulnerability that can be leveraged to craft control flow hijacking attacks. Control Flow Integrity (CFI) provides protection against such attacks. Application of type-based CFI policies requires information regarding the number and type of function arguments. Binary-level type recovery is inherently speculative, which motivates the need for an evaluation framework to assess the effectiveness of binary-level CFI techniques compared with their source-level counterparts, where such type information is fully and accurately accessible. In this work, we develop a novel, generalized and extensible framework to assess how the program analysis information we get from state-of-the-art binary analysis tools affects the efficacy of type-based CFI techniques. We introduce new and insightful metrics to quantitatively compare source independent CFI policies with their ground truth source aware counterparts. We leverage our framework to evaluate binary-level CFI policies implemented using program analysis information extracted from the IDA Pro binary analyzer and compared with the ground truth information obtained from the LLVM compiler, and present our observations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.07148v1-abstract-full').style.display = 'none'; document.getElementById('2401.07148v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 9 figures, 9 tables, Part of this work is to be published in 16th International Symposium on Foundations & Practice of Security (FPS - 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.08509">arXiv:2312.08509</a> <span> [<a href="https://arxiv.org/pdf/2312.08509">pdf</a>, <a href="https://arxiv.org/ps/2312.08509">ps</a>, <a href="https://arxiv.org/format/2312.08509">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Approximating APS under Submodular and XOS valuations with Binary Marginals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+R">Rucha Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+R">Ruta Mehta</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.08509v1-abstract-short" style="display: inline;"> We study the problem of fairly dividing indivisible goods among a set of agents under the fairness notion of Any Price Share (APS). APS is known to dominate the widely studied Maximin share (MMS). Since an exact APS allocation may not exist, the focus has traditionally been on the computation of approximate APS allocations. Babaioff et al. studied the problem under additive valuations, and asked (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08509v1-abstract-full').style.display = 'inline'; document.getElementById('2312.08509v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.08509v1-abstract-full" style="display: none;"> We study the problem of fairly dividing indivisible goods among a set of agents under the fairness notion of Any Price Share (APS). APS is known to dominate the widely studied Maximin share (MMS). Since an exact APS allocation may not exist, the focus has traditionally been on the computation of approximate APS allocations. Babaioff et al. studied the problem under additive valuations, and asked (i) how large can the APS value be compared to the MMS value? and (ii) what guarantees can one achieve beyond additive functions. We partly answer these questions by considering valuations beyond additive, namely submodular and XOS functions, with binary marginals. For the submodular functions with binary marginals, also known as matroid rank functions (MRFs), we show that APS is exactly equal to MMS. Consequently, we get that an exact APS allocation exists and can be computed efficiently while maximizing the social welfare. Complementing this result, we show that it is NP-hard to compute the APS value within a factor of 5/6 for submodular valuations with three distinct marginals of {0, 1/2, 1}. We then consider binary XOS functions, which are immediate generalizations of binary submodular functions in the complement free hierarchy. In contrast to the MRFs setting, MMS and APS values are not equal under this case. Nevertheless, we show that under binary XOS valuations, $MMS \leq APS \leq 2 \cdot MMS + 1$. Further, we show that this is almost the tightest bound we can get using MMS, by giving an instance where $APS \geq 2 \cdot MMS$. The upper bound on APS, implies a ~0.1222-approximation for APS under binary XOS valuations. And the lower bound implies the non-existence of better than 0.5-APS even when agents have identical valuations, which is in sharp contrast to the guaranteed existence of exact MMS allocation when agent valuations are identical. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08509v1-abstract-full').style.display = 'none'; document.getElementById('2312.08509v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.08504">arXiv:2312.08504</a> <span> [<a href="https://arxiv.org/pdf/2312.08504">pdf</a>, <a href="https://arxiv.org/ps/2312.08504">ps</a>, <a href="https://arxiv.org/format/2312.08504">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> 1/2 Approximate MMS Allocation for Separable Piecewise Linear Concave Valuations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chekuri%2C+C">Chandra Chekuri</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+R">Rucha Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+R">Ruta Mehta</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.08504v1-abstract-short" style="display: inline;"> We study fair distribution of a collection of m indivisible goods among a group of n agents, using the widely recognized fairness principles of Maximin Share (MMS) and Any Price Share (APS). These principles have undergone thorough investigation within the context of additive valuations. We explore these notions for valuations that extend beyond additivity. First, we study approximate MMS under… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08504v1-abstract-full').style.display = 'inline'; document.getElementById('2312.08504v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.08504v1-abstract-full" style="display: none;"> We study fair distribution of a collection of m indivisible goods among a group of n agents, using the widely recognized fairness principles of Maximin Share (MMS) and Any Price Share (APS). These principles have undergone thorough investigation within the context of additive valuations. We explore these notions for valuations that extend beyond additivity. First, we study approximate MMS under the separable (piecewise-linear) concave (SPLC) valuations, an important class generalizing additive, where the best known factor was 1/3-MMS. We show that 1/2-MMS allocation exists and can be computed in polynomial time, significantly improving the state-of-the-art. We note that SPLC valuations introduce an elevated level of intricacy in contrast to additive. For instance, the MMS value of an agent can be as high as her value for the entire set of items. Further, the equilibrium computation problem, which is polynomial-time for additive valuations, becomes intractable for SPLC. We use a relax-and-round paradigm that goes through competitive equilibrium and LP relaxation. Our result extends to give (symmetric) 1/2-APS, a stronger guarantee than MMS. APS is a stronger notion that generalizes MMS by allowing agents with arbitrary entitlements. We study the approximation of APS under submodular valuation functions. We design and analyze a simple greedy algorithm using concave extensions of submodular functions. We prove that the algorithm gives a 1/3-APS allocation which matches the current best-known factor. Concave extensions are hard to compute in polynomial time and are, therefore, generally not used in approximation algorithms. Our approach shows a way to utilize it within analysis (while bypassing its computation), and might be of independent interest. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.08504v1-abstract-full').style.display = 'none'; document.getElementById('2312.08504v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in AAAI Conference on Artificial Intelligence, 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.06979">arXiv:2312.06979</a> <span> [<a href="https://arxiv.org/pdf/2312.06979">pdf</a>, <a href="https://arxiv.org/ps/2312.06979">ps</a>, <a href="https://arxiv.org/format/2312.06979">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> On the notion of Hallucinations from the lens of Bias and Validity in Synthetic CXR Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bhardwaj%2C+G">Gauri Bhardwaj</a>, <a href="/search/cs?searchtype=author&query=Govindarajulu%2C+Y">Yuvaraj Govindarajulu</a>, <a href="/search/cs?searchtype=author&query=Narayanan%2C+S">Sundaraparipurnan Narayanan</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pavan Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Manojkumar Parmar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.06979v1-abstract-short" style="display: inline;"> Medical imaging has revolutionized disease diagnosis, yet the potential is hampered by limited access to diverse and privacy-conscious datasets. Open-source medical datasets, while valuable, suffer from data quality and clinical information disparities. Generative models, such as diffusion models, aim to mitigate these challenges. At Stanford, researchers explored the utility of a fine-tuned Stabl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06979v1-abstract-full').style.display = 'inline'; document.getElementById('2312.06979v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.06979v1-abstract-full" style="display: none;"> Medical imaging has revolutionized disease diagnosis, yet the potential is hampered by limited access to diverse and privacy-conscious datasets. Open-source medical datasets, while valuable, suffer from data quality and clinical information disparities. Generative models, such as diffusion models, aim to mitigate these challenges. At Stanford, researchers explored the utility of a fine-tuned Stable Diffusion model (RoentGen) for medical imaging data augmentation. Our work examines specific considerations to expand the Stanford research question, Could Stable Diffusion Solve a Gap in Medical Imaging Data? from the lens of bias and validity of the generated outcomes. We leveraged RoentGen to produce synthetic Chest-XRay (CXR) images and conducted assessments on bias, validity, and hallucinations. Diagnostic accuracy was evaluated by a disease classifier, while a COVID classifier uncovered latent hallucinations. The bias analysis unveiled disparities in classification performance among various subgroups, with a pronounced impact on the Female Hispanic subgroup. Furthermore, incorporating race and gender into input prompts exacerbated fairness issues in the generated images. The quality of synthetic images exhibited variability, particularly in certain disease classes, where there was more significant uncertainty compared to the original images. Additionally, we observed latent hallucinations, with approximately 42% of the images incorrectly indicating COVID, hinting at the presence of hallucinatory elements. These identifications provide new research directions towards interpretability of synthetic CXR images, for further understanding of associated risks and patient safety in medical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.06979v1-abstract-full').style.display = 'none'; document.getElementById('2312.06979v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at 37th Conference on Neural Information Processing Systems (NeurIPS 2023) - "Medical Imaging Meets NeurIPS" Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.05127">arXiv:2308.05127</a> <span> [<a href="https://arxiv.org/pdf/2308.05127">pdf</a>, <a href="https://arxiv.org/format/2308.05127">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Data-Free Model Extraction Attacks in the Context of Object Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+H">Harshit Shah</a>, <a href="/search/cs?searchtype=author&query=G%2C+A">Aravindhan G</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pavan Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Govidarajulu%2C+Y">Yuvaraj Govidarajulu</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Manojkumar Parmar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.05127v1-abstract-short" style="display: inline;"> A significant number of machine learning models are vulnerable to model extraction attacks, which focus on stealing the models by using specially curated queries against the target model. This task is well accomplished by using part of the training data or a surrogate dataset to train a new model that mimics a target model in a white-box environment. In pragmatic situations, however, the target mo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05127v1-abstract-full').style.display = 'inline'; document.getElementById('2308.05127v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.05127v1-abstract-full" style="display: none;"> A significant number of machine learning models are vulnerable to model extraction attacks, which focus on stealing the models by using specially curated queries against the target model. This task is well accomplished by using part of the training data or a surrogate dataset to train a new model that mimics a target model in a white-box environment. In pragmatic situations, however, the target models are trained on private datasets that are inaccessible to the adversary. The data-free model extraction technique replaces this problem when it comes to using queries artificially curated by a generator similar to that used in Generative Adversarial Nets. We propose for the first time, to the best of our knowledge, an adversary black box attack extending to a regression problem for predicting bounding box coordinates in object detection. As part of our study, we found that defining a loss function and using a novel generator setup is one of the key aspects in extracting the target model. We find that the proposed model extraction method achieves significant results by using reasonable queries. The discovery of this object detection vulnerability will support future prospects for securing such models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05127v1-abstract-full').style.display = 'none'; document.getElementById('2308.05127v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to The 14th International Conference on Computer Vision Systems (ICVS 2023), to be published in Springer, Lecture Notes in Computer Science</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.12679">arXiv:2307.12679</a> <span> [<a href="https://arxiv.org/pdf/2307.12679">pdf</a>, <a href="https://arxiv.org/format/2307.12679">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> An Estimator for the Sensitivity to Perturbations of Deep Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Maheshwari%2C+N">Naman Maheshwari</a>, <a href="/search/cs?searchtype=author&query=Malaya%2C+N">Nicholas Malaya</a>, <a href="/search/cs?searchtype=author&query=Moe%2C+S">Scott Moe</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+J+P">Jaydeep P. Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Gurumurthi%2C+S">Sudhanva Gurumurthi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.12679v1-abstract-short" style="display: inline;"> For Deep Neural Networks (DNNs) to become useful in safety-critical applications, such as self-driving cars and disease diagnosis, they must be stable to perturbations in input and model parameters. Characterizing the sensitivity of a DNN to perturbations is necessary to determine minimal bit-width precision that may be used to safely represent the network. However, no general result exists that i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.12679v1-abstract-full').style.display = 'inline'; document.getElementById('2307.12679v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.12679v1-abstract-full" style="display: none;"> For Deep Neural Networks (DNNs) to become useful in safety-critical applications, such as self-driving cars and disease diagnosis, they must be stable to perturbations in input and model parameters. Characterizing the sensitivity of a DNN to perturbations is necessary to determine minimal bit-width precision that may be used to safely represent the network. However, no general result exists that is capable of predicting the sensitivity of a given DNN to round-off error, noise, or other perturbations in input. This paper derives an estimator that can predict such quantities. The estimator is derived via inequalities and matrix norms, and the resulting quantity is roughly analogous to a condition number for the entire neural network. An approximation of the estimator is tested on two Convolutional Neural Networks, AlexNet and VGG-19, using the ImageNet dataset. For each of these networks, the tightness of the estimator is explored via random perturbations and adversarial attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.12679v1-abstract-full').style.display = 'none'; document.getElementById('2307.12679v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Actual work and paper concluded in January 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.03692">arXiv:2307.03692</a> <span> [<a href="https://arxiv.org/pdf/2307.03692">pdf</a>, <a href="https://arxiv.org/format/2307.03692">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=AlShikh%2C+W">Waseem AlShikh</a>, <a href="/search/cs?searchtype=author&query=Daaboul%2C+M">Manhal Daaboul</a>, <a href="/search/cs?searchtype=author&query=Goddard%2C+K">Kirk Goddard</a>, <a href="/search/cs?searchtype=author&query=Imel%2C+B">Brock Imel</a>, <a href="/search/cs?searchtype=author&query=Kamble%2C+K">Kiran Kamble</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Parikshith Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Russak%2C+M">Melisa Russak</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.03692v1-abstract-short" style="display: inline;"> In this paper, we introduce the Instruction Following Score (IFS), a metric that detects language models' ability to follow instructions. The metric has a dual purpose. First, IFS can be used to distinguish between base and instruct models. We benchmark publicly available base and instruct models, and show that the ratio of well formatted responses to partial and full sentences can be an effective… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03692v1-abstract-full').style.display = 'inline'; document.getElementById('2307.03692v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.03692v1-abstract-full" style="display: none;"> In this paper, we introduce the Instruction Following Score (IFS), a metric that detects language models' ability to follow instructions. The metric has a dual purpose. First, IFS can be used to distinguish between base and instruct models. We benchmark publicly available base and instruct models, and show that the ratio of well formatted responses to partial and full sentences can be an effective measure between those two model classes. Secondly, the metric can be used as an early stopping criteria for instruct tuning. We compute IFS for Supervised Fine-Tuning (SFT) of 7B and 13B LLaMA models, showing that models learn to follow instructions relatively early in the training process, and the further finetuning can result in changes in the underlying base model semantics. As an example of semantics change we show the objectivity of model predictions, as defined by an auxiliary metric ObjecQA. We show that in this particular case, semantic changes are the steepest when the IFS tends to plateau. We hope that decomposing instruct tuning into IFS and semantic factors starts a new trend in better controllable instruct tuning and opens possibilities for designing minimal instruct interfaces querying foundation models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03692v1-abstract-full').style.display = 'none'; document.getElementById('2307.03692v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.00438">arXiv:2307.00438</a> <span> [<a href="https://arxiv.org/pdf/2307.00438">pdf</a>, <a href="https://arxiv.org/format/2307.00438">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> One Copy Is All You Need: Resource-Efficient Streaming of Medical Imaging Data at Scale </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Siegel%2C+E">Eliot Siegel</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.00438v1-abstract-short" style="display: inline;"> Large-scale medical imaging datasets have accelerated development of artificial intelligence tools for clinical decision support. However, the large size of these datasets is a bottleneck for users with limited storage and bandwidth. Many users may not even require such large datasets as AI models are often trained on lower resolution images. If users could directly download at their desired resol… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.00438v1-abstract-full').style.display = 'inline'; document.getElementById('2307.00438v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.00438v1-abstract-full" style="display: none;"> Large-scale medical imaging datasets have accelerated development of artificial intelligence tools for clinical decision support. However, the large size of these datasets is a bottleneck for users with limited storage and bandwidth. Many users may not even require such large datasets as AI models are often trained on lower resolution images. If users could directly download at their desired resolution, storage and bandwidth requirements would significantly decrease. However, it is impossible to anticipate every users' requirements and impractical to store the data at multiple resolutions. What if we could store images at a single resolution but send them at different ones? We propose MIST, an open-source framework to operationalize progressive resolution for streaming medical images at multiple resolutions from a single high-resolution copy. We demonstrate that MIST can dramatically reduce imaging infrastructure inefficiencies for hosting and streaming medical images by >90%, while maintaining diagnostic quality for deep learning applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.00438v1-abstract-full').style.display = 'none'; document.getElementById('2307.00438v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 4 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.15617">arXiv:2305.15617</a> <span> [<a href="https://arxiv.org/pdf/2305.15617">pdf</a>, <a href="https://arxiv.org/format/2305.15617">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/s10278-024-01173-z">10.1007/s10278-024-01173-z <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> ISLE: An Intelligent Streaming Framework for High-Throughput AI Inference in Medical Imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Garin%2C+S">Sean Garin</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Siegel%2C+E">Eliot Siegel</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.15617v2-abstract-short" style="display: inline;"> As the adoption of Artificial Intelligence (AI) systems within the clinical environment grows, limitations in bandwidth and compute can create communication bottlenecks when streaming imaging data, leading to delays in patient care and increased cost. As such, healthcare providers and AI vendors will require greater computational infrastructure, therefore dramatically increasing costs. To that end… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15617v2-abstract-full').style.display = 'inline'; document.getElementById('2305.15617v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.15617v2-abstract-full" style="display: none;"> As the adoption of Artificial Intelligence (AI) systems within the clinical environment grows, limitations in bandwidth and compute can create communication bottlenecks when streaming imaging data, leading to delays in patient care and increased cost. As such, healthcare providers and AI vendors will require greater computational infrastructure, therefore dramatically increasing costs. To that end, we developed ISLE, an intelligent streaming framework for high-throughput, compute- and bandwidth- optimized, and cost effective AI inference for clinical decision making at scale. In our experiments, ISLE on average reduced data transmission by 98.02% and decoding time by 98.09%, while increasing throughput by 2,730%. We show that ISLE results in faster turnaround times, and reduced overall cost of data, transmission, and compute, without negatively impacting clinical decision making using AI systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15617v2-abstract-full').style.display = 'none'; document.getElementById('2305.15617v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 3 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.07637">arXiv:2305.07637</a> <span> [<a href="https://arxiv.org/pdf/2305.07637">pdf</a>, <a href="https://arxiv.org/format/2305.07637">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Text2Cohort: Facilitating Intuitive Access to Biomedical Data with Natural Language Cohort Discovery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.07637v3-abstract-short" style="display: inline;"> The Imaging Data Commons (IDC) is a cloud-based database that provides researchers with open access to cancer imaging data, with the goal of facilitating collaboration. However, cohort discovery within the IDC database has a significant technical learning curve. Recently, large language models (LLM) have demonstrated exceptional utility for natural language processing tasks. We developed Text2Coho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07637v3-abstract-full').style.display = 'inline'; document.getElementById('2305.07637v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.07637v3-abstract-full" style="display: none;"> The Imaging Data Commons (IDC) is a cloud-based database that provides researchers with open access to cancer imaging data, with the goal of facilitating collaboration. However, cohort discovery within the IDC database has a significant technical learning curve. Recently, large language models (LLM) have demonstrated exceptional utility for natural language processing tasks. We developed Text2Cohort, a LLM-powered toolkit to facilitate user-friendly natural language cohort discovery in the IDC. Our method translates user input into IDC queries using grounding techniques and returns the query's response. We evaluate Text2Cohort on 50 natural language inputs, from information extraction to cohort discovery. Our toolkit successfully generated responses with an 88% accuracy and 0.94 F1 score. We demonstrate that Text2Cohort can enable researchers to discover and curate cohorts on IDC with high levels of accuracy using natural language in a more intuitive and user-friendly way. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07637v3-abstract-full').style.display = 'none'; document.getElementById('2305.07637v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 3 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.01423">arXiv:2304.01423</a> <span> [<a href="https://arxiv.org/pdf/2304.01423">pdf</a>, <a href="https://arxiv.org/format/2304.01423">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Thematic context vector association based on event uncertainty for Twitter </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khatavkar%2C+V">Vaibhav Khatavkar</a>, <a href="/search/cs?searchtype=author&query=Mane%2C+S">Swapnil Mane</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Parag Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.01423v1-abstract-short" style="display: inline;"> Keyword extraction is a crucial process in text mining. The extraction of keywords with respective contextual events in Twitter data is a big challenge. The challenging issues are mainly because of the informality in the language used. The use of misspelled words, acronyms, and ambiguous terms causes informality. The extraction of keywords with informal language in current systems is pattern based… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.01423v1-abstract-full').style.display = 'inline'; document.getElementById('2304.01423v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.01423v1-abstract-full" style="display: none;"> Keyword extraction is a crucial process in text mining. The extraction of keywords with respective contextual events in Twitter data is a big challenge. The challenging issues are mainly because of the informality in the language used. The use of misspelled words, acronyms, and ambiguous terms causes informality. The extraction of keywords with informal language in current systems is pattern based or event based. In this paper, contextual keywords are extracted using thematic events with the help of data association. The thematic context for events is identified using the uncertainty principle in the proposed system. The thematic contexts are weighed with the help of vectors called thematic context vectors which signifies the event as certain or uncertain. The system is tested on the Twitter COVID-19 dataset and proves to be effective. The system extracts event-specific thematic context vectors from the test dataset and ranks them. The extracted thematic context vectors are used for the clustering of contextual thematic vectors which improves the silhouette coefficient by 0.5% than state of art methods namely TF and TF-IDF. The thematic context vector can be used in other applications like Cyberbullying, sarcasm detection, figurative language detection, etc. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.01423v1-abstract-full').style.display = 'none'; document.getElementById('2304.01423v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.06180">arXiv:2303.06180</a> <span> [<a href="https://arxiv.org/pdf/2303.06180">pdf</a>, <a href="https://arxiv.org/format/2303.06180">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Optimizing Federated Learning for Medical Image Classification on Distributed Non-iid Datasets with Partial Labels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.06180v1-abstract-short" style="display: inline;"> Numerous large-scale chest x-ray datasets have spearheaded expert-level detection of abnormalities using deep learning. However, these datasets focus on detecting a subset of disease labels that could be present, thus making them distributed and non-iid with partial labels. Recent literature has indicated the impact of batch normalization layers on the convergence of federated learning due to doma… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06180v1-abstract-full').style.display = 'inline'; document.getElementById('2303.06180v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.06180v1-abstract-full" style="display: none;"> Numerous large-scale chest x-ray datasets have spearheaded expert-level detection of abnormalities using deep learning. However, these datasets focus on detecting a subset of disease labels that could be present, thus making them distributed and non-iid with partial labels. Recent literature has indicated the impact of batch normalization layers on the convergence of federated learning due to domain shift associated with non-iid data with partial labels. To that end, we propose FedFBN, a federated learning framework that draws inspiration from transfer learning by using pretrained networks as the model backend and freezing the batch normalization layers throughout the training process. We evaluate FedFBN with current FL strategies using synthetic iid toy datasets and large-scale non-iid datasets across scenarios with partial and complete labels. Our results demonstrate that FedFBN outperforms current aggregation strategies for training global models using distributed and non-iid data with partial labels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06180v1-abstract-full').style.display = 'none'; document.getElementById('2303.06180v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 1 algorithm, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.04249">arXiv:2303.04249</a> <span> [<a href="https://arxiv.org/pdf/2303.04249">pdf</a>, <a href="https://arxiv.org/format/2303.04249">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Clark%2C+B">Brandon Clark</a>, <a href="/search/cs?searchtype=author&query=Kerrigan%2C+A">Alec Kerrigan</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P+P">Parth Parag Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Cepeda%2C+V+V">Vicente Vivanco Cepeda</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+M">Mubarak Shah</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.04249v1-abstract-short" style="display: inline;"> Determining the exact latitude and longitude that a photo was taken is a useful and widely applicable task, yet it remains exceptionally difficult despite the accelerated progress of other computer vision tasks. Most previous approaches have opted to learn a single representation of query images, which are then classified at different levels of geographic granularity. These approaches fail to expl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.04249v1-abstract-full').style.display = 'inline'; document.getElementById('2303.04249v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.04249v1-abstract-full" style="display: none;"> Determining the exact latitude and longitude that a photo was taken is a useful and widely applicable task, yet it remains exceptionally difficult despite the accelerated progress of other computer vision tasks. Most previous approaches have opted to learn a single representation of query images, which are then classified at different levels of geographic granularity. These approaches fail to exploit the different visual cues that give context to different hierarchies, such as the country, state, and city level. To this end, we introduce an end-to-end transformer-based architecture that exploits the relationship between different geographic levels (which we refer to as hierarchies) and the corresponding visual scene information in an image through hierarchical cross-attention. We achieve this by learning a query for each geographic hierarchy and scene type. Furthermore, we learn a separate representation for different environmental scenes, as different scenes in the same location are often defined by completely different visual features. We achieve state of the art street level accuracy on 4 standard geo-localization datasets : Im2GPS, Im2GPS3k, YFCC4k, and YFCC26k, as well as qualitatively demonstrate how our method learns different representations for different visual hierarchies and scenes, which has not been demonstrated in the previous methods. These previous testing datasets mostly consist of iconic landmarks or images taken from social media, which makes them either a memorization task, or biased towards certain places. To address this issue we introduce a much harder testing dataset, Google-World-Streets-15k, comprised of images taken from Google Streetview covering the whole planet and present state of the art results. Our code will be made available in the camera-ready version. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.04249v1-abstract-full').style.display = 'none'; document.getElementById('2303.04249v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CVPR 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.00509">arXiv:2302.00509</a> <span> [<a href="https://arxiv.org/pdf/2302.00509">pdf</a>, <a href="https://arxiv.org/format/2302.00509">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Exploring Semantic Perturbations on Grover </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ji%2C+Z">Ziqing Ji</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Neskovic%2C+M">Marko Neskovic</a>, <a href="/search/cs?searchtype=author&query=Nolan%2C+K">Kevin Nolan</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yan Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.00509v2-abstract-short" style="display: inline;"> With news and information being as easy to access as they currently are, it is more important than ever to ensure that people are not mislead by what they read. Recently, the rise of neural fake news (AI-generated fake news) and its demonstrated effectiveness at fooling humans has prompted the development of models to detect it. One such model is the Grover model, which can both detect neural fake… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.00509v2-abstract-full').style.display = 'inline'; document.getElementById('2302.00509v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.00509v2-abstract-full" style="display: none;"> With news and information being as easy to access as they currently are, it is more important than ever to ensure that people are not mislead by what they read. Recently, the rise of neural fake news (AI-generated fake news) and its demonstrated effectiveness at fooling humans has prompted the development of models to detect it. One such model is the Grover model, which can both detect neural fake news to prevent it, and generate it to demonstrate how a model could be misused to fool human readers. In this work we explore the Grover model's fake news detection capabilities by performing targeted attacks through perturbations on input news articles. Through this we test Grover's resilience to these adversarial attacks and expose some potential vulnerabilities which should be addressed in further iterations to ensure it can detect all types of fake news accurately. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.00509v2-abstract-full').style.display = 'none'; document.getElementById('2302.00509v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.11544">arXiv:2301.11544</a> <span> [<a href="https://arxiv.org/pdf/2301.11544">pdf</a>, <a href="https://arxiv.org/format/2301.11544">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Targeted Attacks on Timeseries Forecasting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Govindarajulu%2C+Y">Yuvaraj Govindarajulu</a>, <a href="/search/cs?searchtype=author&query=Amballa%2C+A">Avinash Amballa</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pavan Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Manojkumar Parmar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.11544v1-abstract-short" style="display: inline;"> Real-world deep learning models developed for Time Series Forecasting are used in several critical applications ranging from medical devices to the security domain. Many previous works have shown how deep learning models are prone to adversarial attacks and studied their vulnerabilities. However, the vulnerabilities of time series models for forecasting due to adversarial inputs are not extensivel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.11544v1-abstract-full').style.display = 'inline'; document.getElementById('2301.11544v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.11544v1-abstract-full" style="display: none;"> Real-world deep learning models developed for Time Series Forecasting are used in several critical applications ranging from medical devices to the security domain. Many previous works have shown how deep learning models are prone to adversarial attacks and studied their vulnerabilities. However, the vulnerabilities of time series models for forecasting due to adversarial inputs are not extensively explored. While the attack on a forecasting model might aim to deteriorate the performance of the model, it is more effective, if the attack is focused on a specific impact on the model's output. In this paper, we propose a novel formulation of Directional, Amplitudinal, and Temporal targeted adversarial attacks on time series forecasting models. These targeted attacks create a specific impact on the amplitude and direction of the output prediction. We use the existing adversarial attack techniques from the computer vision domain and adapt them for time series. Additionally, we propose a modified version of the Auto Projected Gradient Descent attack for targeted attacks. We examine the impact of the proposed targeted attacks versus untargeted attacks. We use KS-Tests to statistically demonstrate the impact of the attack. Our experimental results show how targeted attacks on time series models are viable and are more powerful in terms of statistical similarity. It is, hence difficult to detect through statistical methods. We believe that this work opens a new paradigm in the time series forecasting domain and represents an important consideration for developing better defenses. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.11544v1-abstract-full').style.display = 'none'; document.getElementById('2301.11544v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.07074">arXiv:2301.07074</a> <span> [<a href="https://arxiv.org/pdf/2301.07074">pdf</a>, <a href="https://arxiv.org/format/2301.07074">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> SegViz: A federated-learning based framework for multi-organ segmentation on heterogeneous data sets with partial annotations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kanhere%2C+A+U">Adway U. Kanhere</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.07074v3-abstract-short" style="display: inline;"> Segmentation is one of the most primary tasks in deep learning for medical imaging, owing to its multiple downstream clinical applications. However, generating manual annotations for medical images is time-consuming, requires high skill, and is an expensive effort, especially for 3D images. One potential solution is to aggregate knowledge from partially annotated datasets from multiple groups to c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.07074v3-abstract-full').style.display = 'inline'; document.getElementById('2301.07074v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.07074v3-abstract-full" style="display: none;"> Segmentation is one of the most primary tasks in deep learning for medical imaging, owing to its multiple downstream clinical applications. However, generating manual annotations for medical images is time-consuming, requires high skill, and is an expensive effort, especially for 3D images. One potential solution is to aggregate knowledge from partially annotated datasets from multiple groups to collaboratively train global models using Federated Learning. To this end, we propose SegViz, a federated learning-based framework to train a segmentation model from distributed non-i.i.d datasets with partial annotations. The performance of SegViz was compared against training individual models separately on each dataset as well as centrally aggregating all the datasets in one place and training a single model. The SegViz framework using FedBN as the aggregation strategy demonstrated excellent performance on the external BTCV set with dice scores of 0.93, 0.83, 0.55, and 0.75 for segmentation of liver, spleen, pancreas, and kidneys, respectively, significantly ($p<0.05$) better (except spleen) than the dice scores of 0.87, 0.83, 0.42, and 0.48 for the baseline models. In contrast, the central aggregation model significantly ($p<0.05$) performed poorly on the test dataset with dice scores of 0.65, 0, 0.55, and 0.68. Our results demonstrate the potential of the SegViz framework to train multi-task models from distributed datasets with partial labels. All our implementations are open-source and available at https://anonymous.4open.science/r/SegViz-B746 <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.07074v3-abstract-full').style.display = 'none'; document.getElementById('2301.07074v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.06683">arXiv:2301.06683</a> <span> [<a href="https://arxiv.org/pdf/2301.06683">pdf</a>, <a href="https://arxiv.org/format/2301.06683">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.06683v6-abstract-short" style="display: inline;"> Federated learning (FL) is a promising paradigm to collaboratively train a global chest x-ray (CXR) classification model using distributed datasets while preserving patient privacy. A significant, yet relatively underexplored, challenge in FL is class-heterogeneity, where clients have different sets of classes. We propose surgical aggregation, a FL method that uses selective aggregation to collabo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06683v6-abstract-full').style.display = 'inline'; document.getElementById('2301.06683v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.06683v6-abstract-full" style="display: none;"> Federated learning (FL) is a promising paradigm to collaboratively train a global chest x-ray (CXR) classification model using distributed datasets while preserving patient privacy. A significant, yet relatively underexplored, challenge in FL is class-heterogeneity, where clients have different sets of classes. We propose surgical aggregation, a FL method that uses selective aggregation to collaboratively train a global model using distributed, class-heterogeneous datasets. Unlike other methods, our method does not rely on the assumption that clients share the same classes as other clients, know the classes of other clients, or have access to a fully annotated dataset. We evaluate surgical aggregation using class-heterogeneous CXR datasets across IID and non-IID settings. Our results show that our method outperforms current methods and has better generalizability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06683v6-abstract-full').style.display = 'none'; document.getElementById('2301.06683v6-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.06212">arXiv:2211.06212</a> <span> [<a href="https://arxiv.org/pdf/2211.06212">pdf</a>, <a href="https://arxiv.org/format/2211.06212">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> From Competition to Collaboration: Making Toy Datasets on Kaggle Clinically Useful for Chest X-Ray Diagnosis Using Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kanhere%2C+A">Adway Kanhere</a>, <a href="/search/cs?searchtype=author&query=Yi%2C+P+H">Paul H. Yi</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+V+S">Vishwa S. Parekh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.06212v1-abstract-short" style="display: inline;"> Chest X-ray (CXR) datasets hosted on Kaggle, though useful from a data science competition standpoint, have limited utility in clinical use because of their narrow focus on diagnosing one specific disease. In real-world clinical use, multiple diseases need to be considered since they can co-exist in the same patient. In this work, we demonstrate how federated learning (FL) can be used to make thes… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.06212v1-abstract-full').style.display = 'inline'; document.getElementById('2211.06212v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.06212v1-abstract-full" style="display: none;"> Chest X-ray (CXR) datasets hosted on Kaggle, though useful from a data science competition standpoint, have limited utility in clinical use because of their narrow focus on diagnosing one specific disease. In real-world clinical use, multiple diseases need to be considered since they can co-exist in the same patient. In this work, we demonstrate how federated learning (FL) can be used to make these toy CXR datasets from Kaggle clinically useful. Specifically, we train a single FL classification model (`global`) using two separate CXR datasets -- one annotated for presence of pneumonia and the other for presence of pneumothorax (two common and life-threatening conditions) -- capable of diagnosing both. We compare the performance of the global FL model with models trained separately on both datasets (`baseline`) for two different model architectures. On a standard, naive 3-layer CNN architecture, the global FL model achieved AUROC of 0.84 and 0.81 for pneumonia and pneumothorax, respectively, compared to 0.85 and 0.82, respectively, for both baseline models (p>0.05). Similarly, on a pretrained DenseNet121 architecture, the global FL model achieved AUROC of 0.88 and 0.91 for pneumonia and pneumothorax, respectively, compared to 0.89 and 0.91, respectively, for both baseline models (p>0.05). Our results suggest that FL can be used to create global `meta` models to make toy datasets from Kaggle clinically useful, a step forward towards bridging the gap from bench to bedside. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.06212v1-abstract-full').style.display = 'none'; document.getElementById('2211.06212v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted paper for Medical Imaging meet NeurIPS (MedNeurIPS) Workshop 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.08670">arXiv:2208.08670</a> <span> [<a href="https://arxiv.org/pdf/2208.08670">pdf</a>, <a href="https://arxiv.org/format/2208.08670">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Approximation Algorithms for Envy-Free Cake Division with Connected Pieces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Barman%2C+S">Siddharth Barman</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2208.08670v2-abstract-short" style="display: inline;"> Cake cutting is a classic model for studying fair division of a heterogeneous, divisible resource among agents with individual preferences. Addressing cake division under a typical requirement that each agent must receive a connected piece of the cake, we develop approximation algorithms for finding envy-free (fair) cake divisions. In particular, this work improves the state-of-the-art additive ap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.08670v2-abstract-full').style.display = 'inline'; document.getElementById('2208.08670v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.08670v2-abstract-full" style="display: none;"> Cake cutting is a classic model for studying fair division of a heterogeneous, divisible resource among agents with individual preferences. Addressing cake division under a typical requirement that each agent must receive a connected piece of the cake, we develop approximation algorithms for finding envy-free (fair) cake divisions. In particular, this work improves the state-of-the-art additive approximation bound for this fundamental problem. Our results hold for general cake division instances in which the agents' valuations satisfy basic assumptions and are normalized (to have value $1$ for the cake). Furthermore, the developed algorithms execute in polynomial time under the standard Robertson-Webb query model. Prior work has shown that one can efficiently compute a cake division (with connected pieces) in which the additive envy of any agent is at most $1/3$. An efficient algorithm is also known for finding connected cake divisions that are (almost) $1/2$-multiplicatively envy-free. Improving the additive approximation guarantee and maintaining the multiplicative one, we develop a polynomial-time algorithm that computes a connected cake division that is both $\left(\frac{1}{4} +o(1) \right)$-additively envy-free and $\left(\frac{1}{2} - o(1) \right)$-multiplicatively envy-free. Our algorithm is based on the ideas of interval growing and envy-cycle-elimination. In addition, we study cake division instances in which the number of distinct valuations across the agents is parametrically bounded. We show that such cake division instances admit a fully polynomial-time approximation scheme for connected envy-free cake division. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.08670v2-abstract-full').style.display = 'none'; document.getElementById('2208.08670v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.14349">arXiv:2203.14349</a> <span> [<a href="https://arxiv.org/pdf/2203.14349">pdf</a>, <a href="https://arxiv.org/format/2203.14349">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pujari%2C+R">Rajkumar Pujari</a>, <a href="/search/cs?searchtype=author&query=Oveson%2C+E">Erik Oveson</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Priyanka Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Nouri%2C+E">Elnaz Nouri</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2203.14349v1-abstract-short" style="display: inline;"> As large Pre-trained Language Models (PLMs) trained on large amounts of data in an unsupervised manner become more ubiquitous, identifying various types of bias in the text has come into sharp focus. Existing "Stereotype Detection" datasets mainly adopt a diagnostic approach toward large PLMs. Blodgett et. al (2021a) show that there are significant reliability issues with the existing benchmark da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.14349v1-abstract-full').style.display = 'inline'; document.getElementById('2203.14349v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.14349v1-abstract-full" style="display: none;"> As large Pre-trained Language Models (PLMs) trained on large amounts of data in an unsupervised manner become more ubiquitous, identifying various types of bias in the text has come into sharp focus. Existing "Stereotype Detection" datasets mainly adopt a diagnostic approach toward large PLMs. Blodgett et. al (2021a) show that there are significant reliability issues with the existing benchmark datasets. Annotating a reliable dataset requires a precise understanding of the subtle nuances of how stereotypes manifest in text. In this paper, we annotate a focused evaluation set for "Stereotype Detection" that addresses those pitfalls by de-constructing various ways in which stereotypes manifest in text. Further, we present a multi-task model that leverages the abundance of data-rich neighboring tasks such as hate speech detection, offensive language detection, misogyny detection, etc., to improve the empirical performance on "Stereotype Detection". We then propose a reinforcement-learning agent that guides the multi-task learning model by learning to identify the training examples from the neighboring tasks that help the target task the most. We show that the proposed models achieve significant empirical gains over existing baselines on all the tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.14349v1-abstract-full').style.display = 'none'; document.getElementById('2203.14349v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Long paper at ACL 2022 main conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.12337">arXiv:2202.12337</a> <span> [<a href="https://arxiv.org/pdf/2202.12337">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Time Efficient Training of Progressive Generative Adversarial Network using Depthwise Separable Convolution and Super Resolution Generative Adversarial Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Karwande%2C+A">Atharva Karwande</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranesh Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kolhe%2C+T">Tejas Kolhe</a>, <a href="/search/cs?searchtype=author&query=Joshi%2C+A">Akshay Joshi</a>, <a href="/search/cs?searchtype=author&query=Kamble%2C+S">Soham Kamble</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2202.12337v1-abstract-short" style="display: inline;"> Generative Adversarial Networks have been employed successfully to generate high-resolution augmented images of size 1024^2. Although the augmented images generated are unprecedented, the training time of the model is exceptionally high. Conventional GAN requires training of both Discriminator as well as the Generator. In Progressive GAN, which is the current state-of-the-art GAN for image augment… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12337v1-abstract-full').style.display = 'inline'; document.getElementById('2202.12337v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.12337v1-abstract-full" style="display: none;"> Generative Adversarial Networks have been employed successfully to generate high-resolution augmented images of size 1024^2. Although the augmented images generated are unprecedented, the training time of the model is exceptionally high. Conventional GAN requires training of both Discriminator as well as the Generator. In Progressive GAN, which is the current state-of-the-art GAN for image augmentation, instead of training the GAN all at once, a new concept of progressing growing of Discriminator and Generator simultaneously, was proposed. Although the lower stages such as 4x4 and 8x8 train rather quickly, the later stages consume a tremendous amount of time which could take days to finish the model training. In our paper, we propose a novel pipeline that combines Progressive GAN with slight modifications and Super Resolution GAN. Super Resolution GAN up samples low-resolution images to high-resolution images which can prove to be a useful resource to reduce the training time exponentially. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12337v1-abstract-full').style.display = 'none'; document.getElementById('2202.12337v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.00767">arXiv:2110.00767</a> <span> [<a href="https://arxiv.org/pdf/2110.00767">pdf</a>, <a href="https://arxiv.org/format/2110.00767">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Sublinear Approximation Algorithm for Nash Social Welfare with XOS Valuations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Barman%2C+S">Siddharth Barman</a>, <a href="/search/cs?searchtype=author&query=Krishna%2C+A">Anand Krishna</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Narang%2C+S">Shivika Narang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2110.00767v2-abstract-short" style="display: inline;"> We study the problem of allocating indivisible goods among $n$ agents with the objective of maximizing Nash social welfare (NSW). This welfare function is defined as the geometric mean of the agents' valuations and, hence, it strikes a balance between the extremes of social welfare (arithmetic mean) and egalitarian welfare (max-min value). Nash social welfare has been extensively studied in recent… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.00767v2-abstract-full').style.display = 'inline'; document.getElementById('2110.00767v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.00767v2-abstract-full" style="display: none;"> We study the problem of allocating indivisible goods among $n$ agents with the objective of maximizing Nash social welfare (NSW). This welfare function is defined as the geometric mean of the agents' valuations and, hence, it strikes a balance between the extremes of social welfare (arithmetic mean) and egalitarian welfare (max-min value). Nash social welfare has been extensively studied in recent years for various valuation classes. In particular, a notable negative result is known when the agents' valuations are complement-free and are specified via value queries: for XOS valuations, one necessarily requires exponentially many value queries to find any sublinear (in $n$) approximation for NSW. Indeed, this lower bound implies that stronger query models are needed for finding better approximations. Towards this, we utilize demand oracles and XOS oracles; both of these query models are standard and have been used in prior work on social welfare maximization with XOS valuations. We develop the first sublinear approximation algorithm for maximizing Nash social welfare under XOS valuations, specified via demand and XOS oracles. Hence, this work breaks the $O(n)$-approximation barrier for NSW maximization under XOS valuations. We obtain this result by developing a novel connection between NSW and social welfare under a capped version of the agents' valuations. In addition to this insight, which might be of independent interest, this work relies on an intricate combination of multiple technical ideas, including the use of repeated matchings and the discrete moving knife method. In addition, we partially complement the algorithmic result by showing that, under XOS valuations, an exponential number of demand and XOS queries are necessarily required to approximate NSW within a factor of $\left(1 - \frac{1}{e}\right)$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.00767v2-abstract-full').style.display = 'none'; document.getElementById('2110.00767v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">41 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.06947">arXiv:2108.06947</a> <span> [<a href="https://arxiv.org/pdf/2108.06947">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Contextual Mood Analysis with Knowledge Graph Representation for Hindi Song Lyrics in Devanagari Script </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Velankar%2C+M">Makarand Velankar</a>, <a href="/search/cs?searchtype=author&query=Kotian%2C+R">Rachita Kotian</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Parag Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2108.06947v1-abstract-short" style="display: inline;"> Lyrics play a significant role in conveying the song's mood and are information to understand and interpret music communication. Conventional natural language processing approaches use translation of the Hindi text into English for analysis. This approach is not suitable for lyrics as it is likely to lose the inherent intended contextual meaning. Thus, the need was identified to develop a system f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.06947v1-abstract-full').style.display = 'inline'; document.getElementById('2108.06947v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.06947v1-abstract-full" style="display: none;"> Lyrics play a significant role in conveying the song's mood and are information to understand and interpret music communication. Conventional natural language processing approaches use translation of the Hindi text into English for analysis. This approach is not suitable for lyrics as it is likely to lose the inherent intended contextual meaning. Thus, the need was identified to develop a system for Devanagari text analysis. The data set of 300 song lyrics with equal distribution in five different moods is used for the experimentation. The proposed system performs contextual mood analysis of Hindi song lyrics in Devanagari text format. The contextual analysis is stored as a knowledge base, updated using an incremental learning approach with new data. Contextual knowledge graph with moods and associated important contextual terms provides the graphical representation of the lyric data set used. The testing results show 64% accuracy for the mood prediction. This work can be easily extended to applications related to Hindi literary work such as summarization, indexing, contextual retrieval, context-based classification and grouping of documents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.06947v1-abstract-full').style.display = 'none'; document.getElementById('2108.06947v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.09871">arXiv:2107.09871</a> <span> [<a href="https://arxiv.org/pdf/2107.09871">pdf</a>, <a href="https://arxiv.org/ps/2107.09871">ps</a>, <a href="https://arxiv.org/format/2107.09871">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> On Fair and Efficient Allocations of Indivisible Public Goods </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Garg%2C+J">Jugal Garg</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Murhekar%2C+A">Aniket Murhekar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2107.09871v1-abstract-short" style="display: inline;"> We study fair allocation of indivisible public goods subject to cardinality (budget) constraints. In this model, we have n agents and m available public goods, and we want to select $k \leq m$ goods in a fair and efficient manner. We first establish fundamental connections between the models of private goods, public goods, and public decision making by presenting polynomial-time reductions for the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.09871v1-abstract-full').style.display = 'inline'; document.getElementById('2107.09871v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.09871v1-abstract-full" style="display: none;"> We study fair allocation of indivisible public goods subject to cardinality (budget) constraints. In this model, we have n agents and m available public goods, and we want to select $k \leq m$ goods in a fair and efficient manner. We first establish fundamental connections between the models of private goods, public goods, and public decision making by presenting polynomial-time reductions for the popular solution concepts of maximum Nash welfare (MNW) and leximin. These mechanisms are known to provide remarkable fairness and efficiency guarantees in private goods and public decision making settings. We show that they retain these desirable properties even in the public goods case. We prove that MNW allocations provide fairness guarantees of Proportionality up to one good (Prop1), $1/n$ approximation to Round Robin Share (RRS), and the efficiency guarantee of Pareto Optimality (PO). Further, we show that the problems of finding MNW or leximin-optimal allocations are NP-hard, even in the case of constantly many agents, or binary valuations. This is in sharp contrast to the private goods setting that admits polynomial-time algorithms under binary valuations. We also design pseudo-polynomial time algorithms for computing an exact MNW or leximin-optimal allocation for the cases of (i) constantly many agents, and (ii) constantly many goods with additive valuations. We also present an O(n)-factor approximation algorithm for MNW which also satisfies RRS, Prop1, and 1/2-Prop. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.09871v1-abstract-full').style.display = 'none'; document.getElementById('2107.09871v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">25 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.10698">arXiv:2106.10698</a> <span> [<a href="https://arxiv.org/pdf/2106.10698">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Plant Disease Detection Using Image Processing and Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranesh Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Karwande%2C+A">Atharva Karwande</a>, <a href="/search/cs?searchtype=author&query=Kolhe%2C+T">Tejas Kolhe</a>, <a href="/search/cs?searchtype=author&query=Kamble%2C+S">Soham Kamble</a>, <a href="/search/cs?searchtype=author&query=Joshi%2C+A">Akshay Joshi</a>, <a href="/search/cs?searchtype=author&query=Wyawahare%2C+M">Medha Wyawahare</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2106.10698v3-abstract-short" style="display: inline;"> One of the important and tedious task in agricultural practices is the detection of the disease on crops. It requires huge time as well as skilled labor. This paper proposes a smart and efficient technique for detection of crop disease which uses computer vision and machine learning techniques. The proposed system is able to detect 20 different diseases of 5 common plants with 93% accuracy. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.10698v3-abstract-full" style="display: none;"> One of the important and tedious task in agricultural practices is the detection of the disease on crops. It requires huge time as well as skilled labor. This paper proposes a smart and efficient technique for detection of crop disease which uses computer vision and machine learning techniques. The proposed system is able to detect 20 different diseases of 5 common plants with 93% accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.10698v3-abstract-full').style.display = 'none'; document.getElementById('2106.10698v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.08938">arXiv:2106.08938</a> <span> [<a href="https://arxiv.org/pdf/2106.08938">pdf</a>, <a href="https://arxiv.org/format/2106.08938">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Memory Leak Detection Algorithms in the Cloud-based Infrastructure </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jindal%2C+A">Anshul Jindal</a>, <a href="/search/cs?searchtype=author&query=Staab%2C+P">Paul Staab</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+J">Jorge Cardoso</a>, <a href="/search/cs?searchtype=author&query=Gerndt%2C+M">Michael Gerndt</a>, <a href="/search/cs?searchtype=author&query=Podolskiy%2C+V">Vladimir Podolskiy</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2106.08938v1-abstract-short" style="display: inline;"> A memory leak in an application deployed on the cloud can affect the availability and reliability of the application. Therefore, identifying and ultimately resolve it quickly is highly important. However, in the production environment running on the cloud, memory leak detection is a challenge without the knowledge of the application or its internal object allocation details. This paper addresses… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.08938v1-abstract-full').style.display = 'inline'; document.getElementById('2106.08938v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.08938v1-abstract-full" style="display: none;"> A memory leak in an application deployed on the cloud can affect the availability and reliability of the application. Therefore, identifying and ultimately resolve it quickly is highly important. However, in the production environment running on the cloud, memory leak detection is a challenge without the knowledge of the application or its internal object allocation details. This paper addresses this challenge of detection of memory leaks in cloud-based infrastructure without having any internal knowledge by introducing two novel machine learning-based algorithms: Linear Backward Regression (LBR) and Precog and, their two variants: Linear Backward Regression with Change Points Detection (LBRCPD) and Precog with Maximum Filteration (PrecogMF). These algorithms only use one metric i.e the system's memory utilization on which the application is deployed for detection of a memory leak. The developed algorithm's accuracy was tested on 60 virtual machines manually labeled memory utilization data and it was found that the proposed PrecogMF algorithm achieves the highest accuracy score of 85%. The same algorithm also achieves this by decreasing the overall compute time by 80% when compared to LBR's compute time. The paper also presents the different memory leak patterns found in the various memory leak applications and are further classified into different classes based on their visual representation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.08938v1-abstract-full').style.display = 'none'; document.getElementById('2106.08938v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10. pages. arXiv admin note: substantial text overlap with arXiv:2101.09799</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.01272">arXiv:2103.01272</a> <span> [<a href="https://arxiv.org/pdf/2103.01272">pdf</a>, <a href="https://arxiv.org/format/2103.01272">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Geometry-Based Grasping of Vine Tomatoes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=de+Haan%2C+T">Taeke de Haan</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Padmaja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Babuska%2C+R">Robert Babuska</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.01272v1-abstract-short" style="display: inline;"> We propose a geometry-based grasping method for vine tomatoes. It relies on a computer-vision pipeline to identify the required geometric features of the tomatoes and of the truss stem. The grasping method then uses a geometric model of the robotic hand and the truss to determine a suitable grasping location on the stem. This approach allows for grasping tomato trusses without requiring delicate c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.01272v1-abstract-full').style.display = 'inline'; document.getElementById('2103.01272v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.01272v1-abstract-full" style="display: none;"> We propose a geometry-based grasping method for vine tomatoes. It relies on a computer-vision pipeline to identify the required geometric features of the tomatoes and of the truss stem. The grasping method then uses a geometric model of the robotic hand and the truss to determine a suitable grasping location on the stem. This approach allows for grasping tomato trusses without requiring delicate contact sensors or complex mechanistic models and under minimal risk of damaging the tomatoes. Lab experiments were conducted to validate the proposed methods, using an RGB-D camera and a low-cost robotic manipulator. The success rate was 83% to 92%, depending on the type of truss. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.01272v1-abstract-full').style.display = 'none'; document.getElementById('2103.01272v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 12 figures. This work has been submitted to the IEEE for possible publication (IROS + RAL)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.02600">arXiv:2010.02600</a> <span> [<a href="https://arxiv.org/pdf/2010.02600">pdf</a>, <a href="https://arxiv.org/format/2010.02600">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Converting the Point of View of Messages Spoken to Virtual Assistants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lee%2C+I+G">Isabelle G. Lee</a>, <a href="/search/cs?searchtype=author&query=Zu%2C+V">Vera Zu</a>, <a href="/search/cs?searchtype=author&query=Buddi%2C+S+S">Sai Srujana Buddi</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+D">Dennis Liang</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Purva Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Fitzgerald%2C+J+G+M">Jack G. M. Fitzgerald</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2010.02600v2-abstract-short" style="display: inline;"> Virtual Assistants can be quite literal at times. If the user says "tell Bob I love him," most virtual assistants will extract the message "I love him" and send it to the user's contact named Bob, rather than properly converting the message to "I love you." We designed a system to allow virtual assistants to take a voice message from one user, convert the point of view of the message, and then del… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.02600v2-abstract-full').style.display = 'inline'; document.getElementById('2010.02600v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.02600v2-abstract-full" style="display: none;"> Virtual Assistants can be quite literal at times. If the user says "tell Bob I love him," most virtual assistants will extract the message "I love him" and send it to the user's contact named Bob, rather than properly converting the message to "I love you." We designed a system to allow virtual assistants to take a voice message from one user, convert the point of view of the message, and then deliver the result to its target user. We developed a rule-based model, which integrates a linear text classification model, part-of-speech tagging, and constituency parsing with rule-based transformation methods. We also investigated Neural Machine Translation (NMT) approaches, including LSTMs, CopyNet, and T5. We explored 5 metrics to gauge both naturalness and faithfulness automatically, and we chose to use BLEU plus METEOR for faithfulness and relative perplexity using a separately trained language model (GPT) for naturalness. Transformer-Copynet and T5 performed similarly on faithfulness metrics, with T5 achieving slight edge, a BLEU score of 63.8 and a METEOR score of 83.0. CopyNet was the most natural, with a relative perplexity of 1.59. CopyNet also has 37 times fewer parameters than T5. We have publicly released our dataset, which is composed of 46,565 crowd-sourced samples. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.02600v2-abstract-full').style.display = 'none'; document.getElementById('2010.02600v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 11 figures, Findings of EMNLP 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.12541">arXiv:1912.12541</a> <span> [<a href="https://arxiv.org/pdf/1912.12541">pdf</a>, <a href="https://arxiv.org/ps/1912.12541">ps</a>, <a href="https://arxiv.org/format/1912.12541">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> </div> </div> <p class="title is-5 mathjax"> Approximating Nash Social Welfare under Submodular Valuations through (Un)Matchings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Garg%2C+J">Jugal Garg</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+R">Rucha Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.12541v1-abstract-short" style="display: inline;"> We study the problem of approximating maximum Nash social welfare (NSW) when allocating m indivisible items among n asymmetric agents with submodular valuations. The NSW is a well-established notion of fairness and efficiency, defined as the weighted geometric mean of agents' valuations. For special cases of the problem with symmetric agents and additive(-like) valuation functions, approximation a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.12541v1-abstract-full').style.display = 'inline'; document.getElementById('1912.12541v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.12541v1-abstract-full" style="display: none;"> We study the problem of approximating maximum Nash social welfare (NSW) when allocating m indivisible items among n asymmetric agents with submodular valuations. The NSW is a well-established notion of fairness and efficiency, defined as the weighted geometric mean of agents' valuations. For special cases of the problem with symmetric agents and additive(-like) valuation functions, approximation algorithms have been designed using approaches customized for these specific settings, and they fail to extend to more general settings. Hence, no approximation algorithm with factor independent of m is known either for asymmetric agents with additive valuations or for symmetric agents beyond additive(-like) valuations. In this paper, we extend our understanding of the NSW problem to far more general settings. Our main contribution is two approximation algorithms for asymmetric agents with additive and submodular valuations respectively. Both algorithms are simple to understand and involve non-trivial modifications of a greedy repeated matchings approach. Allocations of high valued items are done separately by un-matching certain items and re-matching them, by processes that are different in both algorithms. We show that these approaches achieve approximation factors of O(n) and O(n log n) for additive and submodular case respectively, which is independent of the number of items. For additive valuations, our algorithm outputs an allocation that also achieves the fairness property of envy-free up to one item (EF1). Furthermore, we show that the NSW problem under submodular valuations is strictly harder than all currently known settings with an e/(e-1) factor of the hardness of approximation, even for constantly many agents. For this case, we provide a different approximation algorithm that achieves a factor of e/(e-1), hence resolving it completely. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.12541v1-abstract-full').style.display = 'none'; document.getElementById('1912.12541v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Full version of SODA 2020 paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.03851">arXiv:1912.03851</a> <span> [<a href="https://arxiv.org/pdf/1912.03851">pdf</a>, <a href="https://arxiv.org/ps/1912.03851">ps</a>, <a href="https://arxiv.org/format/1912.03851">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tewari%2C+U+P">Ujwal Padam Tewari</a>, <a href="/search/cs?searchtype=author&query=Bidawatka%2C+V">Vishal Bidawatka</a>, <a href="/search/cs?searchtype=author&query=Raveendran%2C+V">Varsha Raveendran</a>, <a href="/search/cs?searchtype=author&query=Sudhakaran%2C+V">Vinay Sudhakaran</a>, <a href="/search/cs?searchtype=author&query=Shreeshail%2C+S+K">Shreedhar Kodate Shreeshail</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+J+P">Jayanth Prakash Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.03851v4-abstract-short" style="display: inline;"> We use Asynchronous Advantage Actor Critic (A3C) for implementing an AI agent in the controllers that optimize flow of traffic across a single intersection and then extend it to multiple intersections by considering a multi-agent setting. We explore three different methodologies to address the multi-agent problem - (1) use of asynchronous property of A3C to control multiple intersections using a s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.03851v4-abstract-full').style.display = 'inline'; document.getElementById('1912.03851v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.03851v4-abstract-full" style="display: none;"> We use Asynchronous Advantage Actor Critic (A3C) for implementing an AI agent in the controllers that optimize flow of traffic across a single intersection and then extend it to multiple intersections by considering a multi-agent setting. We explore three different methodologies to address the multi-agent problem - (1) use of asynchronous property of A3C to control multiple intersections using a single agent (2) utilise self/competitive play among independent agents across multiple intersections and (3) ingest a global reward function among agents to introduce cooperative behavior between intersections. We observe that (1) & (2) leads to a reduction in traffic congestion. Additionally the use of (3) with (1) & (2) led to a further reduction in congestion. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.03851v4-abstract-full').style.display = 'none'; document.getElementById('1912.03851v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in the NeurIPS 2019 Deep RL Workshop : https://sites.google.com/view/deep-rl-workshop-neurips-2019/home</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.09427">arXiv:1901.09427</a> <span> [<a href="https://arxiv.org/pdf/1901.09427">pdf</a>, <a href="https://arxiv.org/ps/1901.09427">ps</a>, <a href="https://arxiv.org/format/1901.09427">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Fair Division of Indivisible Goods Among Strategic Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Barman%2C+S">Siddharth Barman</a>, <a href="/search/cs?searchtype=author&query=Ghalme%2C+G">Ganesh Ghalme</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+S">Shweta Jain</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Narang%2C+S">Shivika Narang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1901.09427v1-abstract-short" style="display: inline;"> We study fair division of indivisible goods in a single-parameter environment. In particular, we develop truthful social welfare maximizing mechanisms for fairly allocating indivisible goods. Our fairness guarantees are in terms of solution concepts which are tailored to address allocation of indivisible goods and, hence, provide an appropriate framework for fair division of goods. This work speci… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.09427v1-abstract-full').style.display = 'inline'; document.getElementById('1901.09427v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.09427v1-abstract-full" style="display: none;"> We study fair division of indivisible goods in a single-parameter environment. In particular, we develop truthful social welfare maximizing mechanisms for fairly allocating indivisible goods. Our fairness guarantees are in terms of solution concepts which are tailored to address allocation of indivisible goods and, hence, provide an appropriate framework for fair division of goods. This work specifically considers fairness in terms of envy freeness up to one good (EF1), maximin share guarantee (MMS), and Nash social welfare (NSW). Our first result shows that (in a single-parameter environment) the problem of maximizing welfare, subject to the constraint that the allocation of the indivisible goods is EF1, admits a polynomial-time, 1/2-approximate, truthful auction. We further prove that this problem is NP-Hard and, hence, an approximation is warranted. This hardness result also complements prior works which show that an arbitrary EF1 allocation can be computed efficiently. We also establish a bi-criteria approximation guarantee for the problem of maximizing social welfare under MMS constraints. In particular, we develop a truthful auction which efficiently finds an allocation wherein each agent gets a bundle of value at least $\left(1/2 - \varepsilon \right)$ times her maximin share and the welfare of the computed allocation is at least the optimal, here $\varepsilon >0$ is a fixed constant. We complement this result by showing that maximizing welfare is computationally hard even if one aims to only satisfy the MMS constraint approximately. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.09427v1-abstract-full').style.display = 'none'; document.getElementById('1901.09427v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1812.07782">arXiv:1812.07782</a> <span> [<a href="https://arxiv.org/pdf/1812.07782">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Decentralized Periodic Approach for Adaptive Fault Diagnosis in Distributed Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sarna%2C+L">Latika Sarna</a>, <a href="/search/cs?searchtype=author&query=Shenolikar%2C+S">Sumedha Shenolikar</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Poorva Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Deshpande%2C+V">Varsha Deshpande</a>, <a href="/search/cs?searchtype=author&query=Kelkar%2C+S">Supriya Kelkar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1812.07782v1-abstract-short" style="display: inline;"> In this paper, Decentralized Periodic Approach for Adaptive Fault Diagnosis (DP-AFD) algorithm is proposed for fault diagnosis in distributed systems with arbitrary topology. Faulty nodes may be either unresponsive, may have either software or hardware faults. The proposed algorithm detects the faulty nodes situated in geographically distributed locations. This algorithm does not depend on a singl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1812.07782v1-abstract-full').style.display = 'inline'; document.getElementById('1812.07782v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1812.07782v1-abstract-full" style="display: none;"> In this paper, Decentralized Periodic Approach for Adaptive Fault Diagnosis (DP-AFD) algorithm is proposed for fault diagnosis in distributed systems with arbitrary topology. Faulty nodes may be either unresponsive, may have either software or hardware faults. The proposed algorithm detects the faulty nodes situated in geographically distributed locations. This algorithm does not depend on a single node or leader to detect the faults in the system. However, it empowers more than one node to detect the fault-free and faulty nodes in the system. Thus, at the end of each test cycle, every fault-free node acts as a leader to diagnose faults in the system. This feature of the algorithm makes it applicable to any arbitrary network. After every test cycle of the algorithm, all the nodes have knowledge about faulty nodes and each node is tested only once. With this knowledge, there can be redistribution of load, which was earlier assigned to the faulty nodes. Also, the algorithm permits repaired node re-entry and new node entry. In a system of n nodes, the maximum number of faulty nodes can be (n-1) which is detected by DP-AFD algorithm. DP-AFD is periodic in nature which executes test cycles after regular intervals to detect the faulty nodes in the given distributed system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1812.07782v1-abstract-full').style.display = 'none'; document.getElementById('1812.07782v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 December, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 13 figures, 1 table</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> C.2.4; C.2.5; C.2.6 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1812.07771">arXiv:1812.07771</a> <span> [<a href="https://arxiv.org/pdf/1812.07771">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Fault Diagnosis for Distributed Systems using Accuracy Technique </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Poorva Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Deshpande%2C+V">Varsha Deshpande</a>, <a href="/search/cs?searchtype=author&query=Sarna%2C+L">Latika Sarna</a>, <a href="/search/cs?searchtype=author&query=Shenolikar%2C+S">Sumedha Shenolikar</a>, <a href="/search/cs?searchtype=author&query=Kelkar%2C+S">Supriya Kelkar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1812.07771v1-abstract-short" style="display: inline;"> Distributed Systems involve two or more computer systems which may be situated at geographically distinct locations and are connected by a communication network. Due to failures in the communication link, faults arise which may make the entire system dysfunctional. To enable seamless operation of the distributed system, these faults need to be detected and located accurately. This paper examines v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1812.07771v1-abstract-full').style.display = 'inline'; document.getElementById('1812.07771v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1812.07771v1-abstract-full" style="display: none;"> Distributed Systems involve two or more computer systems which may be situated at geographically distinct locations and are connected by a communication network. Due to failures in the communication link, faults arise which may make the entire system dysfunctional. To enable seamless operation of the distributed system, these faults need to be detected and located accurately. This paper examines various techniques of handling faults in distributed systems and proposes and innovative technique which uses percent accuracy for detecting faulty nodes in the system. Every node in the system acts as an initiator and votes for certifying faulty nodes in the system. This certification is done on the basis of percent accuracy value of each faulty node which should exceed a predefined threshold value to qualify node as faulty. As the threshold increases, the number of faulty nodes detected in the system reduces. This is a decentralized approach with no dependency on a single node to act as a leader for diagnosis. This technique is also applicable to ad-hoc networks, which are static in nature. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1812.07771v1-abstract-full').style.display = 'none'; document.getElementById('1812.07771v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 December, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 10 figures, 3 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> C.2.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.04507">arXiv:1811.04507</a> <span> [<a href="https://arxiv.org/pdf/1811.04507">pdf</a>, <a href="https://arxiv.org/format/1811.04507">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> An Interpretable Generative Model for Handwritten Digit Image Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yao Zhu</a>, <a href="/search/cs?searchtype=author&query=Suri%2C+S">Saksham Suri</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pranav Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yueru Chen</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+J">Jiali Duan</a>, <a href="/search/cs?searchtype=author&query=Kuo%2C+C+-+J">C. -C. Jay Kuo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1811.04507v1-abstract-short" style="display: inline;"> An interpretable generative model for handwritten digits synthesis is proposed in this work. Modern image generative models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), are trained by backpropagation (BP). The training process is complex and the underlying mechanism is difficult to explain. We propose an interpretable multi-stage PCA method to achieve the sa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.04507v1-abstract-full').style.display = 'inline'; document.getElementById('1811.04507v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.04507v1-abstract-full" style="display: none;"> An interpretable generative model for handwritten digits synthesis is proposed in this work. Modern image generative models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), are trained by backpropagation (BP). The training process is complex and the underlying mechanism is difficult to explain. We propose an interpretable multi-stage PCA method to achieve the same goal and use handwritten digit images synthesis as an illustrative example. First, we derive principal-component-analysis-based (PCA-based) transform kernels at each stage based on the covariance of its inputs. This results in a sequence of transforms that convert input images of correlated pixels to spectral vectors of uncorrelated components. In other words, it is a whitening process. Then, we can synthesize an image based on random vectors and multi-stage transform kernels through a coloring process. The generative model is a feedforward (FF) design since no BP is used in model parameter determination. Its design complexity is significantly lower, and the whole design process is explainable. Finally, we design an FF generative model using the MNIST dataset, compare synthesis results with those obtained by state-of-the-art GAN and VAE methods, and show that the proposed generative model achieves comparable performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.04507v1-abstract-full').style.display = 'none'; document.getElementById('1811.04507v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1807.09160">arXiv:1807.09160</a> <span> [<a href="https://arxiv.org/pdf/1807.09160">pdf</a>, <a href="https://arxiv.org/format/1807.09160">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Automatically Assessing Vulnerabilities Discovered by Compositional Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ognawala%2C+S">Saahil Ognawala</a>, <a href="/search/cs?searchtype=author&query=Amato%2C+R+N">Ricardo Nales Amato</a>, <a href="/search/cs?searchtype=author&query=Pretschner%2C+A">Alexander Pretschner</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Pooja Kulkarni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1807.09160v1-abstract-short" style="display: inline;"> Testing is the most widely employed method to find vulnerabilities in real-world software programs. Compositional analysis, based on symbolic execution, is an automated testing method to find vulnerabilities in medium- to large-scale programs consisting of many interacting components. However, existing compositional analysis frameworks do not assess the severity of reported vulnerabilities. In thi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.09160v1-abstract-full').style.display = 'inline'; document.getElementById('1807.09160v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1807.09160v1-abstract-full" style="display: none;"> Testing is the most widely employed method to find vulnerabilities in real-world software programs. Compositional analysis, based on symbolic execution, is an automated testing method to find vulnerabilities in medium- to large-scale programs consisting of many interacting components. However, existing compositional analysis frameworks do not assess the severity of reported vulnerabilities. In this paper, we present a framework to analyze vulnerabilities discovered by an existing compositional analysis tool and assign CVSS3 (Common Vulnerability Scoring System v3.0) scores to them, based on various heuristics such as interaction with related components, ease of reachability, complexity of design and likelihood of accepting unsanitized input. By analyzing vulnerabilities reported with CVSS3 scores in the past, we train simple machine learning models. By presenting our interactive framework to developers of popular open-source software and other security experts, we gather feedback on our trained models and further improve the features to increase the accuracy of our predictions. By providing qualitative (based on community feedback) and quantitative (based on prediction accuracy) evidence from 21 open-source programs, we show that our severity prediction framework can effectively assist developers with assessing vulnerabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.09160v1-abstract-full').style.display = 'none'; document.getElementById('1807.09160v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 July, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in the proceedings of the First International Workshop on Machine Learning and Software Engineering in Symbiosis (MASES'18), co-located with IEEE/ACM International Conference on Automated Software Engineering</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Kulkarni%2C+P&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Kulkarni%2C+P&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Kulkarni%2C+P&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository