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 1–29 of 29 results for author: <span class="mathjax">Rajabi, A</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=Rajabi%2C+A">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="Rajabi, A"> </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=Rajabi%2C+A&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="Rajabi, A"> <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> <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/2410.16432">arXiv:2410.16432</a> <span> [<a href="https://arxiv.org/pdf/2410.16432">pdf</a>, <a href="https://arxiv.org/format/2410.16432">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> </div> </div> <p class="title is-5 mathjax"> Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yazdani-Jahromi%2C+M">Mehdi Yazdani-Jahromi</a>, <a href="/search/cs?searchtype=author&query=Yalabadi%2C+A+K">Ali Khodabandeh Yalabadi</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">AmirArsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Tayebi%2C+A">Aida Tayebi</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+I">Ivan Garibay</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+O+O">Ozlem Ozmen Garibay</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="2410.16432v2-abstract-short" style="display: inline;"> The persistent challenge of bias in machine learning models necessitates robust solutions to ensure parity and equal treatment across diverse groups, particularly in classification tasks. Current methods for mitigating bias often result in information loss and an inadequate balance between accuracy and fairness. To address this, we propose a novel methodology grounded in bilevel optimization princ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16432v2-abstract-full').style.display = 'inline'; document.getElementById('2410.16432v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.16432v2-abstract-full" style="display: none;"> The persistent challenge of bias in machine learning models necessitates robust solutions to ensure parity and equal treatment across diverse groups, particularly in classification tasks. Current methods for mitigating bias often result in information loss and an inadequate balance between accuracy and fairness. To address this, we propose a novel methodology grounded in bilevel optimization principles. Our deep learning-based approach concurrently optimizes for both accuracy and fairness objectives, and under certain assumptions, achieving proven Pareto optimal solutions while mitigating bias in the trained model. Theoretical analysis indicates that the upper bound on the loss incurred by this method is less than or equal to the loss of the Lagrangian approach, which involves adding a regularization term to the loss function. We demonstrate the efficacy of our model primarily on tabular datasets such as UCI Adult and Heritage Health. When benchmarked against state-of-the-art fairness methods, our model exhibits superior performance, advancing fairness-aware machine learning solutions and bridging the accuracy-fairness gap. The implementation of FairBiNN is available on https://github.com/yazdanimehdi/FairBiNN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.16432v2-abstract-full').style.display = 'none'; document.getElementById('2410.16432v2-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> 29 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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">Accepted to NeurIPS 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/2406.16388">arXiv:2406.16388</a> <span> [<a href="https://arxiv.org/pdf/2406.16388">pdf</a>, <a href="https://arxiv.org/format/2406.16388">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> PenSLR: Persian end-to-end Sign Language Recognition Using Ensembling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Salmankhah%2C+A">Amirparsa Salmankhah</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirreza Rajabi</a>, <a href="/search/cs?searchtype=author&query=Kheirmand%2C+N">Negin Kheirmand</a>, <a href="/search/cs?searchtype=author&query=Fadaeimanesh%2C+A">Ali Fadaeimanesh</a>, <a href="/search/cs?searchtype=author&query=Tarabkhah%2C+A">Amirreza Tarabkhah</a>, <a href="/search/cs?searchtype=author&query=Kazemzadeh%2C+A">Amirreza Kazemzadeh</a>, <a href="/search/cs?searchtype=author&query=Farbeh%2C+H">Hamed Farbeh</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="2406.16388v1-abstract-short" style="display: inline;"> Sign Language Recognition (SLR) is a fast-growing field that aims to fill the communication gaps between the hearing-impaired and people without hearing loss. Existing solutions for Persian Sign Language (PSL) are limited to word-level interpretations, underscoring the need for more advanced and comprehensive solutions. Moreover, previous work on other languages mainly focuses on manipulating the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16388v1-abstract-full').style.display = 'inline'; document.getElementById('2406.16388v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.16388v1-abstract-full" style="display: none;"> Sign Language Recognition (SLR) is a fast-growing field that aims to fill the communication gaps between the hearing-impaired and people without hearing loss. Existing solutions for Persian Sign Language (PSL) are limited to word-level interpretations, underscoring the need for more advanced and comprehensive solutions. Moreover, previous work on other languages mainly focuses on manipulating the neural network architectures or hardware configurations instead of benefiting from the aggregated results of multiple models. In this paper, we introduce PenSLR, a glove-based sign language system consisting of an Inertial Measurement Unit (IMU) and five flexible sensors powered by a deep learning framework capable of predicting variable-length sequences. We achieve this in an end-to-end manner by leveraging the Connectionist Temporal Classification (CTC) loss function, eliminating the need for segmentation of input signals. To further enhance its capabilities, we propose a novel ensembling technique by leveraging a multiple sequence alignment algorithm known as Star Alignment. Furthermore, we introduce a new PSL dataset, including 16 PSL signs with more than 3000 time-series samples in total. We utilize this dataset to evaluate the performance of our system based on four word-level and sentence-level metrics. Our evaluations show that PenSLR achieves a remarkable word accuracy of 94.58% and 96.70% in subject-independent and subject-dependent setups, respectively. These achievements are attributable to our ensembling algorithm, which not only boosts the word-level performance by 0.51% and 1.32% in the respective scenarios but also yields significant enhancements of 1.46% and 4.00%, respectively, in sentence-level accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16388v1-abstract-full').style.display = 'none'; document.getElementById('2406.16388v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.08695">arXiv:2402.08695</a> <span> [<a href="https://arxiv.org/pdf/2402.08695">pdf</a>, <a href="https://arxiv.org/format/2402.08695">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sahabandu%2C+D">Dinuka Sahabandu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiaojun Xu</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Luyao Niu</a>, <a href="/search/cs?searchtype=author&query=Ramasubramanian%2C+B">Bhaskar Ramasubramanian</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bo Li</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2402.08695v1-abstract-short" style="display: inline;"> We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ensure (1) high accuracy on both trigger-embedded and clean samples and (2) bypass detection. Our approach is based on an observation that the high dimensionality of the DNN parameters provides sufficient degrees of freedom… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08695v1-abstract-full').style.display = 'inline'; document.getElementById('2402.08695v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.08695v1-abstract-full" style="display: none;"> We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ensure (1) high accuracy on both trigger-embedded and clean samples and (2) bypass detection. Our approach is based on an observation that the high dimensionality of the DNN parameters provides sufficient degrees of freedom to simultaneously achieve these objectives. We also enable SOTA detectors to be adaptive by allowing retraining to recalibrate their parameters, thus modeling a co-evolution of parameters of a Trojaned model and detectors. We then show that this co-evolution can be modeled as an iterative game, and prove that the resulting (optimal) solution of this interactive game leads to the adversary successfully achieving the above objectives. In addition, we provide a greedy algorithm for the adversary to select a minimum number of input samples for embedding triggers. We show that for cross-entropy or log-likelihood loss functions used by the DNNs, the greedy algorithm provides provable guarantees on the needed number of trigger-embedded input samples. Extensive experiments on four diverse datasets -- MNIST, CIFAR-10, CIFAR-100, and SpeechCommand -- reveal that the adversary effectively evades four SOTA output-based Trojaned model detectors: MNTD, NeuralCleanse, STRIP, and TABOR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08695v1-abstract-full').style.display = 'none'; document.getElementById('2402.08695v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.01114">arXiv:2402.01114</a> <span> [<a href="https://arxiv.org/pdf/2402.01114">pdf</a>, <a href="https://arxiv.org/format/2402.01114">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"> Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Pimple%2C+R">Reeya Pimple</a>, <a href="/search/cs?searchtype=author&query=Janardhanan%2C+A">Aiswarya Janardhanan</a>, <a href="/search/cs?searchtype=author&query=Asokraj%2C+S">Surudhi Asokraj</a>, <a href="/search/cs?searchtype=author&query=Ramasubramanian%2C+B">Bhaskar Ramasubramanian</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2402.01114v1-abstract-short" style="display: inline;"> Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is unexplored. A class of privacy attacks called membership inference attacks (MIAs) aim to determine whether a given sample belongs to the training dataset (member) o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01114v1-abstract-full').style.display = 'inline'; document.getElementById('2402.01114v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01114v1-abstract-full" style="display: none;"> Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is unexplored. A class of privacy attacks called membership inference attacks (MIAs) aim to determine whether a given sample belongs to the training dataset (member) or not (nonmember). We introduce Double-Dip, a systematic empirical study investigating the use of TL (Stage-1) combined with randomization (Stage-2) to thwart MIAs on overfitted DNNs without degrading classification accuracy. Our study examines the roles of shared feature space and parameter values between source and target models, number of frozen layers, and complexity of pretrained models. We evaluate Double-Dip on three (Target, Source) dataset paris: (i) (CIFAR-10, ImageNet), (ii) (GTSRB, ImageNet), (iii) (CelebA, VGGFace2). We consider four publicly available pretrained DNNs: (a) VGG-19, (b) ResNet-18, (c) Swin-T, and (d) FaceNet. Our experiments demonstrate that Stage-1 reduces adversary success while also significantly increasing classification accuracy of nonmembers against an adversary with either white-box or black-box DNN model access, attempting to carry out SOTA label-only MIAs. After Stage-2, success of an adversary carrying out a label-only MIA is further reduced to near 50%, bringing it closer to a random guess and showing the effectiveness of Double-Dip. Stage-2 of Double-Dip also achieves lower ASR and higher classification accuracy than regularization and differential privacy-based methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01114v1-abstract-full').style.display = 'none'; document.getElementById('2402.01114v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.15673">arXiv:2308.15673</a> <span> [<a href="https://arxiv.org/pdf/2308.15673">pdf</a>, <a href="https://arxiv.org/format/2308.15673">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> MDTD: A Multi Domain Trojan Detector for Deep Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Asokraj%2C+S">Surudhi Asokraj</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+F">Fengqing Jiang</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Luyao Niu</a>, <a href="/search/cs?searchtype=author&query=Ramasubramanian%2C+B">Bhaskar Ramasubramanian</a>, <a href="/search/cs?searchtype=author&query=Ritcey%2C+J">Jim Ritcey</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2308.15673v2-abstract-short" style="display: inline;"> Machine learning models that use deep neural networks (DNNs) are vulnerable to backdoor attacks. An adversary carrying out a backdoor attack embeds a predefined perturbation called a trigger into a small subset of input samples and trains the DNN such that the presence of the trigger in the input results in an adversary-desired output class. Such adversarial retraining however needs to ensure that… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.15673v2-abstract-full').style.display = 'inline'; document.getElementById('2308.15673v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.15673v2-abstract-full" style="display: none;"> Machine learning models that use deep neural networks (DNNs) are vulnerable to backdoor attacks. An adversary carrying out a backdoor attack embeds a predefined perturbation called a trigger into a small subset of input samples and trains the DNN such that the presence of the trigger in the input results in an adversary-desired output class. Such adversarial retraining however needs to ensure that outputs for inputs without the trigger remain unaffected and provide high classification accuracy on clean samples. In this paper, we propose MDTD, a Multi-Domain Trojan Detector for DNNs, which detects inputs containing a Trojan trigger at testing time. MDTD does not require knowledge of trigger-embedding strategy of the attacker and can be applied to a pre-trained DNN model with image, audio, or graph-based inputs. MDTD leverages an insight that input samples containing a Trojan trigger are located relatively farther away from a decision boundary than clean samples. MDTD estimates the distance to a decision boundary using adversarial learning methods and uses this distance to infer whether a test-time input sample is Trojaned or not. We evaluate MDTD against state-of-the-art Trojan detection methods across five widely used image-based datasets: CIFAR100, CIFAR10, GTSRB, SVHN, and Flowers102; four graph-based datasets: AIDS, WinMal, Toxicant, and COLLAB; and the SpeechCommand audio dataset. MDTD effectively identifies samples that contain different types of Trojan triggers. We evaluate MDTD against adaptive attacks where an adversary trains a robust DNN to increase (decrease) distance of benign (Trojan) inputs from a decision boundary. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.15673v2-abstract-full').style.display = 'none'; document.getElementById('2308.15673v2-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 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 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">Accepted to ACM Conference on Computer and Communications Security (ACM CCS) 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/2304.10848">arXiv:2304.10848</a> <span> [<a href="https://arxiv.org/pdf/2304.10848">pdf</a>, <a href="https://arxiv.org/format/2304.10848">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</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="Data Structures and Algorithms">cs.DS</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/10.1145/3583131.3590390">10.1145/3583131.3590390 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> How Well Does the Metropolis Algorithm Cope With Local Optima? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Doerr%2C+B">Benjamin Doerr</a>, <a href="/search/cs?searchtype=author&query=Houssaini%2C+T+E+G+E">Taha El Ghazi El Houssaini</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirhossein Rajabi</a>, <a href="/search/cs?searchtype=author&query=Witt%2C+C">Carsten Witt</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="2304.10848v2-abstract-short" style="display: inline;"> The Metropolis algorithm (MA) is a classic stochastic local search heuristic. It avoids getting stuck in local optima by occasionally accepting inferior solutions. To better and in a rigorous manner understand this ability, we conduct a mathematical runtime analysis of the MA on the CLIFF benchmark. Apart from one local optimum, cliff functions are monotonically increasing towards the global optim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.10848v2-abstract-full').style.display = 'inline'; document.getElementById('2304.10848v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.10848v2-abstract-full" style="display: none;"> The Metropolis algorithm (MA) is a classic stochastic local search heuristic. It avoids getting stuck in local optima by occasionally accepting inferior solutions. To better and in a rigorous manner understand this ability, we conduct a mathematical runtime analysis of the MA on the CLIFF benchmark. Apart from one local optimum, cliff functions are monotonically increasing towards the global optimum. Consequently, to optimize a cliff function, the MA only once needs to accept an inferior solution. Despite seemingly being an ideal benchmark for the MA to profit from its main working principle, our mathematical runtime analysis shows that this hope does not come true. Even with the optimal temperature (the only parameter of the MA), the MA optimizes most cliff functions less efficiently than simple elitist evolutionary algorithms (EAs), which can only leave the local optimum by generating a superior solution possibly far away. This result suggests that our understanding of why the MA is often very successful in practice is not yet complete. Our work also suggests to equip the MA with global mutation operators, an idea supported by our preliminary experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.10848v2-abstract-full').style.display = 'none'; document.getElementById('2304.10848v2-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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">To appear in the proceedings of GECCO 2023. With appendix containing all proofs. 28 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/2212.01688">arXiv:2212.01688</a> <span> [<a href="https://arxiv.org/pdf/2212.01688">pdf</a>, <a href="https://arxiv.org/format/2212.01688">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"> LDL: A Defense for Label-Based Membership Inference Attacks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Sahabandu%2C+D">Dinuka Sahabandu</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Luyao Niu</a>, <a href="/search/cs?searchtype=author&query=Ramasubramanian%2C+B">Bhaskar Ramasubramanian</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2212.01688v2-abstract-short" style="display: inline;"> The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitting. Overfitted models have been shown to be susceptible to query-based attacks such as membership inference attacks (MIAs). MIAs aim to determine whether a sample belongs to the dataset used to train a classifier (membe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.01688v2-abstract-full').style.display = 'inline'; document.getElementById('2212.01688v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.01688v2-abstract-full" style="display: none;"> The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitting. Overfitted models have been shown to be susceptible to query-based attacks such as membership inference attacks (MIAs). MIAs aim to determine whether a sample belongs to the dataset used to train a classifier (members) or not (nonmembers). Recently, a new class of label based MIAs (LAB MIAs) was proposed, where an adversary was only required to have knowledge of predicted labels of samples. Developing a defense against an adversary carrying out a LAB MIA on DNN models that cannot be retrained remains an open problem. We present LDL, a light weight defense against LAB MIAs. LDL works by constructing a high-dimensional sphere around queried samples such that the model decision is unchanged for (noisy) variants of the sample within the sphere. This sphere of label-invariance creates ambiguity and prevents a querying adversary from correctly determining whether a sample is a member or a nonmember. We analytically characterize the success rate of an adversary carrying out a LAB MIA when LDL is deployed, and show that the formulation is consistent with experimental observations. We evaluate LDL on seven datasets -- CIFAR-10, CIFAR-100, GTSRB, Face, Purchase, Location, and Texas -- with varying sizes of training data. All of these datasets have been used by SOTA LAB MIAs. Our experiments demonstrate that LDL reduces the success rate of an adversary carrying out a LAB MIA in each case. We empirically compare LDL with defenses against LAB MIAs that require retraining of DNN models, and show that LDL performs favorably despite not needing to retrain the DNNs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.01688v2-abstract-full').style.display = 'none'; document.getElementById('2212.01688v2-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 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">to appear in ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS 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/2209.08648">arXiv:2209.08648</a> <span> [<a href="https://arxiv.org/pdf/2209.08648">pdf</a>, <a href="https://arxiv.org/format/2209.08648">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"> Through a fair looking-glass: mitigating bias in image datasets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirarsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Yazdani-Jahromi%2C+M">Mehdi Yazdani-Jahromi</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+O+O">Ozlem Ozmen Garibay</a>, <a href="/search/cs?searchtype=author&query=Sukthankar%2C+G">Gita Sukthankar</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="2209.08648v1-abstract-short" style="display: inline;"> With the recent growth in computer vision applications, the question of how fair and unbiased they are has yet to be explored. There is abundant evidence that the bias present in training data is reflected in the models, or even amplified. Many previous methods for image dataset de-biasing, including models based on augmenting datasets, are computationally expensive to implement. In this study, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.08648v1-abstract-full').style.display = 'inline'; document.getElementById('2209.08648v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.08648v1-abstract-full" style="display: none;"> With the recent growth in computer vision applications, the question of how fair and unbiased they are has yet to be explored. There is abundant evidence that the bias present in training data is reflected in the models, or even amplified. Many previous methods for image dataset de-biasing, including models based on augmenting datasets, are computationally expensive to implement. In this study, we present a fast and effective model to de-bias an image dataset through reconstruction and minimizing the statistical dependence between intended variables. Our architecture includes a U-net to reconstruct images, combined with a pre-trained classifier which penalizes the statistical dependence between target attribute and the protected attribute. We evaluate our proposed model on CelebA dataset, compare the results with a state-of-the-art de-biasing method, and show that the model achieves a promising fairness-accuracy combination. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.08648v1-abstract-full').style.display = 'none'; document.getElementById('2209.08648v1-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.05937">arXiv:2207.05937</a> <span> [<a href="https://arxiv.org/pdf/2207.05937">pdf</a>, <a href="https://arxiv.org/format/2207.05937">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Game of Trojans: A Submodular Byzantine Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sahabandu%2C+D">Dinuka Sahabandu</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+L">Luyao Niu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+B">Bo Li</a>, <a href="/search/cs?searchtype=author&query=Ramasubramanian%2C+B">Bhaskar Ramasubramanian</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2207.05937v1-abstract-short" style="display: inline;"> Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attackers have been shown to be effective against them. In this paper, we aim to answer the questions considering an intelligent and adaptive adversary: (i) What is the minimal amount of instances required to be Trojaned by a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.05937v1-abstract-full').style.display = 'inline'; document.getElementById('2207.05937v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.05937v1-abstract-full" style="display: none;"> Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attackers have been shown to be effective against them. In this paper, we aim to answer the questions considering an intelligent and adaptive adversary: (i) What is the minimal amount of instances required to be Trojaned by a strong attacker? and (ii) Is it possible for such an attacker to bypass strong detection mechanisms? We provide an analytical characterization of adversarial capability and strategic interactions between the adversary and detection mechanism that take place in such models. We characterize adversary capability in terms of the fraction of the input dataset that can be embedded with a Trojan trigger. We show that the loss function has a submodular structure, which leads to the design of computationally efficient algorithms to determine this fraction with provable bounds on optimality. We propose a Submodular Trojan algorithm to determine the minimal fraction of samples to inject a Trojan trigger. To evade detection of the Trojaned model, we model strategic interactions between the adversary and Trojan detection mechanism as a two-player game. We show that the adversary wins the game with probability one, thus bypassing detection. We establish this by proving that output probability distributions of a Trojan model and a clean model are identical when following the Min-Max (MM) Trojan algorithm. We perform extensive evaluations of our algorithms on MNIST, CIFAR-10, and EuroSAT datasets. The results show that (i) with Submodular Trojan algorithm, the adversary needs to embed a Trojan trigger into a very small fraction of samples to achieve high accuracy on both Trojan and clean samples, and (ii) the MM Trojan algorithm yields a trained Trojan model that evades detection with probability 1. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.05937v1-abstract-full').style.display = 'none'; document.getElementById('2207.05937v1-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 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">Submitted to GameSec 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/2204.02097">arXiv:2204.02097</a> <span> [<a href="https://arxiv.org/pdf/2204.02097">pdf</a>, <a href="https://arxiv.org/ps/2204.02097">ps</a>, <a href="https://arxiv.org/format/2204.02097">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</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/s00453-023-01135-x">10.1007/s00453-023-01135-x <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Simulated Annealing is a Polynomial-Time Approximation Scheme for the Minimum Spanning Tree Problem </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Doerr%2C+B">Benjamin Doerr</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirhossein Rajabi</a>, <a href="/search/cs?searchtype=author&query=Witt%2C+C">Carsten Witt</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="2204.02097v2-abstract-short" style="display: inline;"> We prove that Simulated Annealing with an appropriate cooling schedule computes arbitrarily tight constant-factor approximations to the minimum spanning tree problem in polynomial time. This result was conjectured by Wegener (2005). More precisely, denoting by $n, m, w_{\max}$, and $w_{\min}$ the number of vertices and edges as well as the maximum and minimum edge weight of the MST instance, we pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.02097v2-abstract-full').style.display = 'inline'; document.getElementById('2204.02097v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.02097v2-abstract-full" style="display: none;"> We prove that Simulated Annealing with an appropriate cooling schedule computes arbitrarily tight constant-factor approximations to the minimum spanning tree problem in polynomial time. This result was conjectured by Wegener (2005). More precisely, denoting by $n, m, w_{\max}$, and $w_{\min}$ the number of vertices and edges as well as the maximum and minimum edge weight of the MST instance, we prove that simulated annealing with initial temperature $T_0 \ge w_{\max}$ and multiplicative cooling schedule with factor $1-1/\ell$, where $\ell = 蠅(mn\ln(m))$, with probability at least $1-1/m$ computes in time $O(\ell (\ln\ln (\ell) + \ln(T_0/w_{\min}) ))$ a spanning tree with weight at most $1+魏$ times the optimum weight, where $1+魏= \frac{(1+o(1))\ln(\ell m)}{\ln(\ell) -\ln (mn\ln (m))}$. Consequently, for any $蔚>0$, we can choose $\ell$ in such a way that a $(1+蔚)$-approximation is found in time $O((mn\ln(n))^{1+1/蔚+o(1)}(\ln\ln n + \ln(T_0/w_{\min})))$ with probability at least $1-1/m$. In the special case of so-called $(1+蔚)$-separated weights, this algorithm computes an optimal solution (again in time $O( (mn\ln(n))^{1+1/蔚+o(1)}(\ln\ln n + \ln(T_0/w_{\min})))$), which is a significant speed-up over Wegener's runtime guarantee of $O(m^{8 + 8/蔚})$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.02097v2-abstract-full').style.display = 'none'; document.getElementById('2204.02097v2-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">19 pages. Extended version of a paper at GECCO 2022. This version is accepted for publication in Algorithmica</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Simulated annealing is a polynomial-time approximation scheme for the minimum spanning tree problem. Algorithmica. 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.15506">arXiv:2203.15506</a> <span> [<a href="https://arxiv.org/pdf/2203.15506">pdf</a>, <a href="https://arxiv.org/format/2203.15506">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Ramasubramanian%2C+B">Bhaskar Ramasubramanian</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2203.15506v1-abstract-short" style="display: inline;"> Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the neural network to misclassify the input to a (single) target class, while classifying other inputs without a trigger correctly. ML models that contain a backdoor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.15506v1-abstract-full').style.display = 'inline'; document.getElementById('2203.15506v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.15506v1-abstract-full" style="display: none;"> Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the neural network to misclassify the input to a (single) target class, while classifying other inputs without a trigger correctly. ML models that contain a backdoor are called Trojan models. Backdoors can have severe consequences in safety-critical cyber and cyber physical systems when only the outputs of the model are available. Defense mechanisms have been developed and illustrated to be able to distinguish between outputs from a Trojan model and a non-Trojan model in the case of a single-target backdoor attack with accuracy > 96 percent. Understanding the limitations of a defense mechanism requires the construction of examples where the mechanism fails. Current single-target backdoor attacks require one trigger per target class. We introduce a new, more general attack that will enable a single trigger to result in misclassification to more than one target class. Such a misclassification will depend on the true (actual) class that the input belongs to. We term this category of attacks multi-target backdoor attacks. We demonstrate that a Trojan model with either a single-target or multi-target trigger can be trained so that the accuracy of a defense mechanism that seeks to distinguish between outputs coming from a Trojan and a non-Trojan model will be reduced. Our approach uses the non-Trojan model as a teacher for the Trojan model and solves a min-max optimization problem between the Trojan model and defense mechanism. Empirical evaluations demonstrate that our training procedure reduces the accuracy of a state-of-the-art defense mechanism from >96 to 0 percent. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.15506v1-abstract-full').style.display = 'none'; document.getElementById('2203.15506v1-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 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">Submitted to 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/2203.10165">arXiv:2203.10165</a> <span> [<a href="https://arxiv.org/pdf/2203.10165">pdf</a>, <a href="https://arxiv.org/format/2203.10165">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Privacy-Preserving Reinforcement Learning Beyond Expectation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Ramasubramanian%2C+B">Bhaskar Ramasubramanian</a>, <a href="/search/cs?searchtype=author&query=Maruf%2C+A+A">Abdullah Al Maruf</a>, <a href="/search/cs?searchtype=author&query=Poovendran%2C+R">Radha Poovendran</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="2203.10165v1-abstract-short" style="display: inline;"> Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. In such a setting, it is important to align system (or agent) behaviors with the preferences of one or more human users. We consider the case when an agent has to learn behaviors in an unknown environment. Our goal is to capture two defining characteristics of humans:… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.10165v1-abstract-full').style.display = 'inline'; document.getElementById('2203.10165v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.10165v1-abstract-full" style="display: none;"> Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. In such a setting, it is important to align system (or agent) behaviors with the preferences of one or more human users. We consider the case when an agent has to learn behaviors in an unknown environment. Our goal is to capture two defining characteristics of humans: i) a tendency to assess and quantify risk, and ii) a desire to keep decision making hidden from external parties. We incorporate cumulative prospect theory (CPT) into the objective of a reinforcement learning (RL) problem for the former. For the latter, we use differential privacy. We design an algorithm to enable an RL agent to learn policies to maximize a CPT-based objective in a privacy-preserving manner and establish guarantees on the privacy of value functions learned by the algorithm when rewards are sufficiently close. This is accomplished through adding a calibrated noise using a Gaussian process mechanism at each step. Through empirical evaluations, we highlight a privacy-utility tradeoff and demonstrate that the RL agent is able to learn behaviors that are aligned with that of a human user in the same environment in a privacy-preserving manner <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.10165v1-abstract-full').style.display = 'none'; document.getElementById('2203.10165v1-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 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">Submitted to conference. arXiv admin note: text overlap with arXiv:2104.00540</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.07593">arXiv:2203.07593</a> <span> [<a href="https://arxiv.org/pdf/2203.07593">pdf</a>, <a href="https://arxiv.org/format/2203.07593">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> </div> </div> <p class="title is-5 mathjax"> Distraction is All You Need for Fairness </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yazdani-Jahromi%2C+M">Mehdi Yazdani-Jahromi</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">AmirArsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Yalabadi%2C+A+K">Ali Khodabandeh Yalabadi</a>, <a href="/search/cs?searchtype=author&query=Tayebi%2C+A">Aida Tayebi</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+O+O">Ozlem Ozmen Garibay</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="2203.07593v3-abstract-short" style="display: inline;"> Bias in training datasets must be managed for various groups in classification tasks to ensure parity or equal treatment. With the recent growth in artificial intelligence models and their expanding role in automated decision-making, ensuring that these models are not biased is vital. There is an abundance of evidence suggesting that these models could contain or even amplify the bias present in t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.07593v3-abstract-full').style.display = 'inline'; document.getElementById('2203.07593v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.07593v3-abstract-full" style="display: none;"> Bias in training datasets must be managed for various groups in classification tasks to ensure parity or equal treatment. With the recent growth in artificial intelligence models and their expanding role in automated decision-making, ensuring that these models are not biased is vital. There is an abundance of evidence suggesting that these models could contain or even amplify the bias present in the data on which they are trained, inherent to their objective function and learning algorithms; Many researchers direct their attention to this issue in different directions, namely, changing data to be statistically independent, adversarial training for restricting the capabilities of a particular competitor who aims to maximize parity, etc. These methods result in information loss and do not provide a suitable balance between accuracy and fairness or do not ensure limiting the biases in training. To this end, we propose a powerful strategy for training deep learning models called the Distraction module, which can be theoretically proven effective in controlling bias from affecting the classification results. This method can be utilized with different data types (e.g., Tabular, images, graphs, etc.). We demonstrate the potency of the proposed method by testing it on UCI Adult and Heritage Health datasets (tabular), POKEC-Z, POKEC-N and NBA datasets (graph), and CelebA dataset (vision). Using state-of-the-art methods proposed in the fairness literature for each dataset, we exhibit our model is superior to these proposed methods in minimizing bias and maintaining accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.07593v3-abstract-full').style.display = 'none'; document.getElementById('2203.07593v3-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.12158">arXiv:2201.12158</a> <span> [<a href="https://arxiv.org/pdf/2201.12158">pdf</a>, <a href="https://arxiv.org/format/2201.12158">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</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/10.1162/evco\_a\_00313">10.1162/evco\_a\_00313 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Stagnation Detection Meets Fast Mutation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Doerr%2C+B">Benjamin Doerr</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirhossein Rajabi</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="2201.12158v2-abstract-short" style="display: inline;"> Two mechanisms have recently been proposed that can significantly speed up finding distant improving solutions via mutation, namely using a random mutation rate drawn from a heavy-tailed distribution ("fast mutation", Doerr et al. (2017)) and increasing the mutation strength based on stagnation detection (Rajabi and Witt (2020)). Whereas the latter can obtain the asymptotically best probability of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.12158v2-abstract-full').style.display = 'inline'; document.getElementById('2201.12158v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.12158v2-abstract-full" style="display: none;"> Two mechanisms have recently been proposed that can significantly speed up finding distant improving solutions via mutation, namely using a random mutation rate drawn from a heavy-tailed distribution ("fast mutation", Doerr et al. (2017)) and increasing the mutation strength based on stagnation detection (Rajabi and Witt (2020)). Whereas the latter can obtain the asymptotically best probability of finding a single desired solution in a given distance, the former is more robust and performs much better when many improving solutions in some distance exist. In this work, we propose a mutation strategy that combines ideas of both mechanisms. We show that it can also obtain the best possible probability of finding a single distant solution. However, when several improving solutions exist, it can outperform both the stagnation-detection approach and fast mutation. The new operator is more than an interleaving of the two previous mechanisms and it also outperforms any such interleaving. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.12158v2-abstract-full').style.display = 'none'; document.getElementById('2201.12158v2-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">28 pages. Full version of a paper appearing at EvoCOP 2022</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Theoretical Computer Science 946: 113670 (2023) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.00666">arXiv:2109.00666</a> <span> [<a href="https://arxiv.org/pdf/2109.00666">pdf</a>, <a href="https://arxiv.org/format/2109.00666">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> </div> </div> <p class="title is-5 mathjax"> TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirarsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+O+O">Ozlem Ozmen Garibay</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="2109.00666v1-abstract-short" style="display: inline;"> With the increasing reliance on automated decision making, the issue of algorithmic fairness has gained increasing importance. In this paper, we propose a Generative Adversarial Network for tabular data generation. The model includes two phases of training. In the first phase, the model is trained to accurately generate synthetic data similar to the reference dataset. In the second phase we modify… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.00666v1-abstract-full').style.display = 'inline'; document.getElementById('2109.00666v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.00666v1-abstract-full" style="display: none;"> With the increasing reliance on automated decision making, the issue of algorithmic fairness has gained increasing importance. In this paper, we propose a Generative Adversarial Network for tabular data generation. The model includes two phases of training. In the first phase, the model is trained to accurately generate synthetic data similar to the reference dataset. In the second phase we modify the value function to add fairness constraint, and continue training the network to generate data that is both accurate and fair. We test our results in both cases of unconstrained, and constrained fair data generation. In the unconstrained case, i.e. when the model is only trained in the first phase and is only meant to generate accurate data following the same joint probability distribution of the real data, the results show that the model beats state-of-the-art GANs proposed in the literature to produce synthetic tabular data. Also, in the constrained case in which the first phase of training is followed by the second phase, we train the network and test it on four datasets studied in the fairness literature and compare our results with another state-of-the-art pre-processing method, and present the promising results that it achieves. Comparing to other studies utilizing GANs for fair data generation, our model is comparably more stable by using only one critic, and also by avoiding major problems of original GAN model, such as mode-dropping and non-convergence, by implementing a Wasserstein GAN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.00666v1-abstract-full').style.display = 'none'; document.getElementById('2109.00666v1-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.04395">arXiv:2104.04395</a> <span> [<a href="https://arxiv.org/pdf/2104.04395">pdf</a>, <a href="https://arxiv.org/format/2104.04395">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Stagnation Detection in Highly Multimodal Fitness Landscapes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirhossein Rajabi</a>, <a href="/search/cs?searchtype=author&query=Witt%2C+C">Carsten Witt</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="2104.04395v3-abstract-short" style="display: inline;"> Stagnation detection has been proposed as a mechanism for randomized search heuristics to escape from local optima by automatically increasing the size of the neighborhood to find the so-called gap size, i.e., the distance to the next improvement. Its usefulness has mostly been considered in simple multimodal landscapes with few local optima that could be crossed one after another. In multimodal l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.04395v3-abstract-full').style.display = 'inline'; document.getElementById('2104.04395v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.04395v3-abstract-full" style="display: none;"> Stagnation detection has been proposed as a mechanism for randomized search heuristics to escape from local optima by automatically increasing the size of the neighborhood to find the so-called gap size, i.e., the distance to the next improvement. Its usefulness has mostly been considered in simple multimodal landscapes with few local optima that could be crossed one after another. In multimodal landscapes with a more complex location of optima of similar gap size, stagnation detection suffers from the fact that the neighborhood size is frequently reset to $1$ without using gap sizes that were promising in the past. In this paper, we investigate a new mechanism called radius memory which can be added to stagnation detection to control the search radius more carefully by giving preference to values that were successful in the past. We implement this idea in an algorithm called SD-RLS$^{\text{m}}$ and show compared to previous variants of stagnation detection that it yields speed-ups for linear functions under uniform constraints and the minimum spanning tree problem. Moreover, its running time does not significantly deteriorate on unimodal functions and a generalization of the Jump benchmark. Finally, we present experimental results carried out to study SD-RLS$^{\text{m}}$ and compare it with other algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.04395v3-abstract-full').style.display = 'none'; document.getElementById('2104.04395v3-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 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">28 pages. Full version of a paper appearing at GECCO 2021. arXiv admin note: text overlap with arXiv:2101.12054</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.12054">arXiv:2101.12054</a> <span> [<a href="https://arxiv.org/pdf/2101.12054">pdf</a>, <a href="https://arxiv.org/format/2101.12054">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</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/10.1007/978-3-030-72904-2_10">10.1007/978-3-030-72904-2_10 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Stagnation Detection with Randomized Local Search </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirhossein Rajabi</a>, <a href="/search/cs?searchtype=author&query=Witt%2C+C">Carsten Witt</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="2101.12054v2-abstract-short" style="display: inline;"> Recently a mechanism called stagnation detection was proposed that automatically adjusts the mutation rate of evolutionary algorithms when they encounter local optima. The so-called $SD-(1+1)EA$ introduced by Rajabi and Witt (GECCO 2020) adds stagnation detection to the classical $(1+1)EA$ with standard bit mutation, which flips each bit independently with some mutation rate, and raises the mutati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.12054v2-abstract-full').style.display = 'inline'; document.getElementById('2101.12054v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.12054v2-abstract-full" style="display: none;"> Recently a mechanism called stagnation detection was proposed that automatically adjusts the mutation rate of evolutionary algorithms when they encounter local optima. The so-called $SD-(1+1)EA$ introduced by Rajabi and Witt (GECCO 2020) adds stagnation detection to the classical $(1+1)EA$ with standard bit mutation, which flips each bit independently with some mutation rate, and raises the mutation rate when the algorithm is likely to have encountered local optima. In this paper, we investigate stagnation detection in the context of the $k$-bit flip operator of randomized local search that flips $k$ bits chosen uniformly at random and let stagnation detection adjust the parameter $k$. We obtain improved runtime results compared to the $SD-(1+1)EA$ amounting to a speed-up of up to $e=2.71\dots$ Moreover, we propose additional schemes that prevent infinite optimization times even if the algorithm misses a working choice of $k$ due to unlucky events. Finally, we present an example where standard bit mutation still outperforms the local $k$-bit flip with stagnation detection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.12054v2-abstract-full').style.display = 'none'; document.getElementById('2101.12054v2-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> 8 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">24 pages. Full version of a paper appearing at EvoCOP 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.09123">arXiv:2011.09123</a> <span> [<a href="https://arxiv.org/pdf/2011.09123">pdf</a>, <a href="https://arxiv.org/format/2011.09123">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"> Adversarial Profiles: Detecting Out-Distribution & Adversarial Samples in Pre-trained CNNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Bobba%2C+R+B">Rakesh B. Bobba</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="2011.09123v1-abstract-short" style="display: inline;"> Despite high accuracy of Convolutional Neural Networks (CNNs), they are vulnerable to adversarial and out-distribution examples. There are many proposed methods that tend to detect or make CNNs robust against these fooling examples. However, most such methods need access to a wide range of fooling examples to retrain the network or to tune detection parameters. Here, we propose a method to detect… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.09123v1-abstract-full').style.display = 'inline'; document.getElementById('2011.09123v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.09123v1-abstract-full" style="display: none;"> Despite high accuracy of Convolutional Neural Networks (CNNs), they are vulnerable to adversarial and out-distribution examples. There are many proposed methods that tend to detect or make CNNs robust against these fooling examples. However, most such methods need access to a wide range of fooling examples to retrain the network or to tune detection parameters. Here, we propose a method to detect adversarial and out-distribution examples against a pre-trained CNN without needing to retrain the CNN or needing access to a wide variety of fooling examples. To this end, we create adversarial profiles for each class using only one adversarial attack generation technique. We then wrap a detector around the pre-trained CNN that applies the created adversarial profile to each input and uses the output to decide whether or not the input is legitimate. Our initial evaluation of this approach using MNIST dataset show that adversarial profile based detection is effective in detecting at least 92 of out-distribution examples and 59% of adversarial examples. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.09123v1-abstract-full').style.display = 'none'; document.getElementById('2011.09123v1-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 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Accepted on DSN Workshop on Dependable and Secure Machine Learning 2019</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> DSN Workshop on Dependable and Secure Machine Learning (DSML 2019) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.01188">arXiv:2009.01188</a> <span> [<a href="https://arxiv.org/pdf/2009.01188">pdf</a>, <a href="https://arxiv.org/format/2009.01188">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> A Stance Data Set on Polarized Conversations on Twitter about the Efficacy of Hydroxychloroquine as a Treatment for COVID-19 </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mutlu%2C+E+%C3%87">Ece 脟i臒dem Mutlu</a>, <a href="/search/cs?searchtype=author&query=Oghaz%2C+T+A">Toktam A. Oghaz</a>, <a href="/search/cs?searchtype=author&query=Jasser%2C+J">Jasser Jasser</a>, <a href="/search/cs?searchtype=author&query=T%C3%BCt%C3%BCnc%C3%BCler%2C+E">Ege T眉t眉nc眉ler</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirarsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Tayebi%2C+A">Aida Tayebi</a>, <a href="/search/cs?searchtype=author&query=Ozmen%2C+O">Ozlem Ozmen</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+I">Ivan Garibay</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="2009.01188v2-abstract-short" style="display: inline;"> At the time of this study, the SARS-CoV-2 virus that caused the COVID-19 pandemic has spread significantly across the world. Considering the uncertainty about policies, health risks, financial difficulties, etc. the online media, specially the Twitter platform, is experiencing a high volume of activity related to this pandemic. Among the hot topics, the polarized debates about unconfirmed medicine… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.01188v2-abstract-full').style.display = 'inline'; document.getElementById('2009.01188v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.01188v2-abstract-full" style="display: none;"> At the time of this study, the SARS-CoV-2 virus that caused the COVID-19 pandemic has spread significantly across the world. Considering the uncertainty about policies, health risks, financial difficulties, etc. the online media, specially the Twitter platform, is experiencing a high volume of activity related to this pandemic. Among the hot topics, the polarized debates about unconfirmed medicines for the treatment and prevention of the disease have attracted significant attention from online media users. In this work, we present a stance data set, COVID-CQ, of user-generated content on Twitter in the context of COVID-19. We investigated more than 14 thousand tweets and manually annotated the opinions of the tweet initiators regarding the use of "chloroquine" and "hydroxychloroquine" for the treatment or prevention of COVID-19. To the best of our knowledge, COVID-CQ is the first data set of Twitter users' stances in the context of the COVID-19 pandemic, and the largest Twitter data set on users' stances towards a claim, in any domain. We have made this data set available to the research community via GitHub. We expect this data set to be useful for many research purposes, including stance detection, evolution and dynamics of opinions regarding this outbreak, and changes in opinions in response to the exogenous shocks such as policy decisions and events. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.01188v2-abstract-full').style.display = 'none'; document.getElementById('2009.01188v2-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 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">11 pages, 3 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/2008.12723">arXiv:2008.12723</a> <span> [<a href="https://arxiv.org/pdf/2008.12723">pdf</a>, <a href="https://arxiv.org/format/2008.12723">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> CD-SEIZ: Cognition-Driven SEIZ Compartmental Model for the Prediction of Information Cascades on Twitter </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mutlu%2C+E+%C3%87">Ece 脟i臒dem Mutlu</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirarsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+I">Ivan Garibay</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="2008.12723v1-abstract-short" style="display: inline;"> Information spreading social media platforms has become ubiquitous in our lives due to viral information propagation regardless of its veracity. Some information cascades turn out to be viral since they circulated rapidly on the Internet. The uncontrollable virality of manipulated or disorientated true information (fake news) might be quite harmful, while the spread of the true news is advantageou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.12723v1-abstract-full').style.display = 'inline'; document.getElementById('2008.12723v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.12723v1-abstract-full" style="display: none;"> Information spreading social media platforms has become ubiquitous in our lives due to viral information propagation regardless of its veracity. Some information cascades turn out to be viral since they circulated rapidly on the Internet. The uncontrollable virality of manipulated or disorientated true information (fake news) might be quite harmful, while the spread of the true news is advantageous, especially in emergencies. We tackle the problem of predicting information cascades by presenting a novel variant of SEIZ (Susceptible/ Exposed/ Infected/ Skeptics) model that outperforms the original version by taking into account the cognitive processing depth of users. We define an information cascade as the set of social media users' reactions to the original content which requires at least minimal physical and cognitive effort; therefore, we considered retweet/ reply/ quote (mention) activities and tested our framework on the Syrian White Helmets Twitter data set from April 1st, 2018 to April 30th, 2019. In the prediction of cascade pattern via traditional compartmental models, all the activities are grouped, and their summation is taken into account; however, transition rates between compartments should vary according to the activity type since their requirements of physical and cognitive efforts are not same. Based on this assumption, we design a cognition-driven SEIZ (CD-SEIZ) model in the prediction of information cascades on Twitter. We tested SIS, SEIZ, and CD-SEIZ models on 1000 Twitter cascades and found that CD-SEIZ has a significantly low fitting error and provides a statistically more accurate estimation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.12723v1-abstract-full').style.display = 'none'; document.getElementById('2008.12723v1-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 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.09126">arXiv:2006.09126</a> <span> [<a href="https://arxiv.org/pdf/2006.09126">pdf</a>, <a href="https://arxiv.org/format/2006.09126">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</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/10.1007/978-3-030-58112-1_46">10.1007/978-3-030-58112-1_46 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Evolutionary Algorithms with Self-adjusting Asymmetric Mutation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirhossein Rajabi</a>, <a href="/search/cs?searchtype=author&query=Witt%2C+C">Carsten Witt</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="2006.09126v1-abstract-short" style="display: inline;"> Evolutionary Algorithms (EAs) and other randomized search heuristics are often considered as unbiased algorithms that are invariant with respect to different transformations of the underlying search space. However, if a certain amount of domain knowledge is available the use of biased search operators in EAs becomes viable. We consider a simple (1+1) EA for binary search spaces and analyze an asym… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.09126v1-abstract-full').style.display = 'inline'; document.getElementById('2006.09126v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.09126v1-abstract-full" style="display: none;"> Evolutionary Algorithms (EAs) and other randomized search heuristics are often considered as unbiased algorithms that are invariant with respect to different transformations of the underlying search space. However, if a certain amount of domain knowledge is available the use of biased search operators in EAs becomes viable. We consider a simple (1+1) EA for binary search spaces and analyze an asymmetric mutation operator that can treat zero- and one-bits differently. This operator extends previous work by Jansen and Sudholt (ECJ 18(1), 2010) by allowing the operator asymmetry to vary according to the success rate of the algorithm. Using a self-adjusting scheme that learns an appropriate degree of asymmetry, we show improved runtime results on the class of functions OneMax$_a$ describing the number of matching bits with a fixed target $a\in\{0,1\}^n$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.09126v1-abstract-full').style.display = 'none'; document.getElementById('2006.09126v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">16 pages. An extended abstract of this paper will be published in the proceedings of PPSN 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/2005.08321">arXiv:2005.08321</a> <span> [<a href="https://arxiv.org/pdf/2005.08321">pdf</a>, <a href="https://arxiv.org/format/2005.08321">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Abbasi%2C+M">Mahdieh Abbasi</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Gagne%2C+C">Christian Gagne</a>, <a href="/search/cs?searchtype=author&query=Bobba%2C+R+B">Rakesh B. Bobba</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="2005.08321v1-abstract-short" style="display: inline;"> We aim at demonstrating the influence of diversity in the ensemble of CNNs on the detection of black-box adversarial instances and hardening the generation of white-box adversarial attacks. To this end, we propose an ensemble of diverse specialized CNNs along with a simple voting mechanism. The diversity in this ensemble creates a gap between the predictive confidences of adversaries and those of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.08321v1-abstract-full').style.display = 'inline'; document.getElementById('2005.08321v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.08321v1-abstract-full" style="display: none;"> We aim at demonstrating the influence of diversity in the ensemble of CNNs on the detection of black-box adversarial instances and hardening the generation of white-box adversarial attacks. To this end, we propose an ensemble of diverse specialized CNNs along with a simple voting mechanism. The diversity in this ensemble creates a gap between the predictive confidences of adversaries and those of clean samples, making adversaries detectable. We then analyze how diversity in such an ensemble of specialists may mitigate the risk of the black-box and white-box adversarial examples. Using MNIST and CIFAR-10, we empirically verify the ability of our ensemble to detect a large portion of well-known black-box adversarial examples, which leads to a significant reduction in the risk rate of adversaries, at the expense of a small increase in the risk rate of clean samples. Moreover, we show that the success rate of generating white-box attacks by our ensemble is remarkably decreased compared to a vanilla CNN and an ensemble of vanilla CNNs, highlighting the beneficial role of diversity in the ensemble for developing more robust models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.08321v1-abstract-full').style.display = 'none'; document.getElementById('2005.08321v1-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> 17 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">Published by Springer in the Lecture Notes in Artificial Intelligence</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.03266">arXiv:2004.03266</a> <span> [<a href="https://arxiv.org/pdf/2004.03266">pdf</a>, <a href="https://arxiv.org/format/2004.03266">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</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/10.1145/3377930.3389833">10.1145/3377930.3389833 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Self-Adjusting Evolutionary Algorithms for Multimodal Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirhossein Rajabi</a>, <a href="/search/cs?searchtype=author&query=Witt%2C+C">Carsten Witt</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="2004.03266v2-abstract-short" style="display: inline;"> Recent theoretical research has shown that self-adjusting and self-adaptive mechanisms can provably outperform static settings in evolutionary algorithms for binary search spaces. However, the vast majority of these studies focuses on unimodal functions which do not require the algorithm to flip several bits simultaneously to make progress. In fact, existing self-adjusting algorithms are not desig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.03266v2-abstract-full').style.display = 'inline'; document.getElementById('2004.03266v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.03266v2-abstract-full" style="display: none;"> Recent theoretical research has shown that self-adjusting and self-adaptive mechanisms can provably outperform static settings in evolutionary algorithms for binary search spaces. However, the vast majority of these studies focuses on unimodal functions which do not require the algorithm to flip several bits simultaneously to make progress. In fact, existing self-adjusting algorithms are not designed to detect local optima and do not have any obvious benefit to cross large Hamming gaps. We suggest a mechanism called stagnation detection that can be added as a module to existing evolutionary algorithms (both with and without prior self-adjusting algorithms). Added to a simple (1+1) EA, we prove an expected runtime on the well-known Jump benchmark that corresponds to an asymptotically optimal parameter setting and outperforms other mechanisms for multimodal optimization like heavy-tailed mutation. We also investigate the module in the context of a self-adjusting (1+$位$) EA and show that it combines the previous benefits of this algorithm on unimodal problems with more efficient multimodal optimization. To explore the limitations of the approach, we additionally present an example where both self-adjusting mechanisms, including stagnation detection, do not help to find a beneficial setting of the mutation rate. Finally, we investigate our module for stagnation detection experimentally. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.03266v2-abstract-full').style.display = 'none'; document.getElementById('2004.03266v2-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 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">26 pages. Full version of a paper appearing at GECCO 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/2004.00379">arXiv:2004.00379</a> <span> [<a href="https://arxiv.org/pdf/2004.00379">pdf</a>, <a href="https://arxiv.org/format/2004.00379">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Resistance of communities against disinformation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirarsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Talebzadehhosseini%2C+S">Seyyedmilad Talebzadehhosseini</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+I">Ivan Garibay</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="2004.00379v1-abstract-short" style="display: inline;"> The spread of disinformation is considered a big threat to societies and has recently received unprecedented attention. In this paper we propose an agent-based model to simulate dissemination of a conspiracy in a population. The model is able to compare the resistance of different network structures against the activity of conspirators. Results show that connectedness of network structure and cent… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.00379v1-abstract-full').style.display = 'inline'; document.getElementById('2004.00379v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.00379v1-abstract-full" style="display: none;"> The spread of disinformation is considered a big threat to societies and has recently received unprecedented attention. In this paper we propose an agent-based model to simulate dissemination of a conspiracy in a population. The model is able to compare the resistance of different network structures against the activity of conspirators. Results show that connectedness of network structure and centrality of conspirators are of crucial importance in preventing conspiracies from becoming widespread. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.00379v1-abstract-full').style.display = 'none'; document.getElementById('2004.00379v1-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 March, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1910.08650">arXiv:1910.08650</a> <span> [<a href="https://arxiv.org/pdf/1910.08650">pdf</a>, <a href="https://arxiv.org/format/1910.08650">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Toward Metrics for Differentiating Out-of-Distribution Sets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Abbasi%2C+M">Mahdieh Abbasi</a>, <a href="/search/cs?searchtype=author&query=Shui%2C+C">Changjian Shui</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Gagne%2C+C">Christian Gagne</a>, <a href="/search/cs?searchtype=author&query=Bobba%2C+R">Rakesh Bobba</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="1910.08650v3-abstract-short" style="display: inline;"> Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, some recent works have demonstrated the gains of leveraging available OOD sets for training end-to-end calibrated CNNs. However, a critical question remains unanswered in these works: how to differentiate OOD sets for selec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.08650v3-abstract-full').style.display = 'inline'; document.getElementById('1910.08650v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1910.08650v3-abstract-full" style="display: none;"> Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, some recent works have demonstrated the gains of leveraging available OOD sets for training end-to-end calibrated CNNs. However, a critical question remains unanswered in these works: how to differentiate OOD sets for selecting the most effective one(s) that induce training such CNNs with high detection rates on unseen OOD sets? To address this pivotal question, we provide a criterion based on generalization errors of Augmented-CNN, a vanilla CNN with an added extra class employed for rejection, on in-distribution and unseen OOD sets. However, selecting the most effective OOD set by directly optimizing this criterion incurs a huge computational cost. Instead, we propose three novel computationally-efficient metrics for differentiating between OOD sets according to their "protection" level of in-distribution sub-manifolds. We empirically verify that the most protective OOD sets -- selected according to our metrics -- lead to A-CNNs with significantly lower generalization errors than the A-CNNs trained on the least protective ones. We also empirically show the effectiveness of a protective OOD set for training well-generalized confidence-calibrated vanilla CNNs. These results confirm that 1) all OOD sets are not equally effective for training well-performing end-to-end models (i.e., A-CNNs and calibrated CNNs) for OOD detection tasks and 2) the protection level of OOD sets is a viable factor for recognizing the most effective one. Finally, across the image classification tasks, we exhibit A-CNN trained on the most protective OOD set can also detect black-box FGS adversarial examples as their distance (measured by our metrics) is becoming larger from the protected sub-manifolds. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.08650v3-abstract-full').style.display = 'none'; document.getElementById('1910.08650v3-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 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">Workshop on Safety and Robustness in Decision Making, NeurIPS 2019</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ECAI 2020 : 24th European Conference on Artificial Intelligence </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.03425">arXiv:1901.03425</a> <span> [<a href="https://arxiv.org/pdf/1901.03425">pdf</a>, <a href="https://arxiv.org/format/1901.03425">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</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/10.3390/make2040036">10.3390/make2040036 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Review on Learning and Extracting Graph Features for Link Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mutlu%2C+E+C">Ece C. Mutlu</a>, <a href="/search/cs?searchtype=author&query=Oghaz%2C+T+A">Toktam A. Oghaz</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Amirarsalan Rajabi</a>, <a href="/search/cs?searchtype=author&query=Garibay%2C+I">Ivan Garibay</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="1901.03425v5-abstract-short" style="display: inline;"> Link prediction in complex networks has attracted considerable attention from interdisciplinary research communities, due to its ubiquitous applications in biological networks, social networks, transportation networks, telecommunication networks, and, recently, knowledge graphs. Numerous studies utilized link prediction approaches in order sto find missing links or predict the likelihood of future… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.03425v5-abstract-full').style.display = 'inline'; document.getElementById('1901.03425v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.03425v5-abstract-full" style="display: none;"> Link prediction in complex networks has attracted considerable attention from interdisciplinary research communities, due to its ubiquitous applications in biological networks, social networks, transportation networks, telecommunication networks, and, recently, knowledge graphs. Numerous studies utilized link prediction approaches in order sto find missing links or predict the likelihood of future links as well as employed for reconstruction networks, recommender systems, privacy control, etc. This work presents an extensive review of state-of-art methods and algorithms proposed on this subject and categorizes them into four main categories: similarity-based methods, probabilistic methods, relational models, and learning-based methods. Additionally, a collection of network data sets has been presented in this paper, which can be used in order to study link prediction. We conclude this study with a discussion of recent developments and future research directions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.03425v5-abstract-full').style.display = 'none'; document.getElementById('1901.03425v5-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> 20 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">29 pages, 7 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/1808.08282">arXiv:1808.08282</a> <span> [<a href="https://arxiv.org/pdf/1808.08282">pdf</a>, <a href="https://arxiv.org/format/1808.08282">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"> Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Abbasi%2C+M">Mahdieh Abbasi</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Mozafari%2C+A+S">Azadeh Sadat Mozafari</a>, <a href="/search/cs?searchtype=author&query=Bobba%2C+R+B">Rakesh B. Bobba</a>, <a href="/search/cs?searchtype=author&query=Gagne%2C+C">Christian Gagne</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="1808.08282v2-abstract-short" style="display: inline;"> Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes into pre-defined known classes. Further, they are also vulnerable to adversarial examples. We are relating these two issues through the tendency of CNNs… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1808.08282v2-abstract-full').style.display = 'inline'; document.getElementById('1808.08282v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1808.08282v2-abstract-full" style="display: none;"> Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes into pre-defined known classes. Further, they are also vulnerable to adversarial examples. We are relating these two issues through the tendency of CNNs to over-generalize for areas of the input space not covered well by the training set. We show that a CNN augmented with an extra output class can act as a simple yet effective end-to-end model for controlling over-generalization. As an appropriate training set for the extra class, we introduce two resources that are computationally efficient to obtain: a representative natural out-distribution set and interpolated in-distribution samples. To help select a representative natural out-distribution set among available ones, we propose a simple measurement to assess an out-distribution set's fitness. We also demonstrate that training such an augmented CNN with representative out-distribution natural datasets and some interpolated samples allows it to better handle a wide range of unseen out-distribution samples and black-box adversarial examples without training it on any adversaries. Finally, we show that generation of white-box adversarial attacks using our proposed augmented CNN can become harder, as the attack algorithms have to get around the rejection regions when generating actual adversaries. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1808.08282v2-abstract-full').style.display = 'none'; document.getElementById('1808.08282v2-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 October, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 August, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1804.08794">arXiv:1804.08794</a> <span> [<a href="https://arxiv.org/pdf/1804.08794">pdf</a>, <a href="https://arxiv.org/format/1804.08794">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Abbasi%2C+M">Mahdieh Abbasi</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</a>, <a href="/search/cs?searchtype=author&query=Gagn%C3%A9%2C+C">Christian Gagn茅</a>, <a href="/search/cs?searchtype=author&query=Bobba%2C+R+B">Rakesh B. Bobba</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="1804.08794v2-abstract-short" style="display: inline;"> Detection and rejection of adversarial examples in security sensitive and safety-critical systems using deep CNNs is essential. In this paper, we propose an approach to augment CNNs with out-distribution learning in order to reduce misclassification rate by rejecting adversarial examples. We empirically show that our augmented CNNs can either reject or classify correctly most adversarial examples… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.08794v2-abstract-full').style.display = 'inline'; document.getElementById('1804.08794v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1804.08794v2-abstract-full" style="display: none;"> Detection and rejection of adversarial examples in security sensitive and safety-critical systems using deep CNNs is essential. In this paper, we propose an approach to augment CNNs with out-distribution learning in order to reduce misclassification rate by rejecting adversarial examples. We empirically show that our augmented CNNs can either reject or classify correctly most adversarial examples generated using well-known methods ( >95% for MNIST and >75% for CIFAR-10 on average). Furthermore, we achieve this without requiring to train using any specific type of adversarial examples and without sacrificing the accuracy of models on clean samples significantly (< 4%). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.08794v2-abstract-full').style.display = 'none'; document.getElementById('1804.08794v2-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 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1706.00941">arXiv:1706.00941</a> <span> [<a href="https://arxiv.org/pdf/1706.00941">pdf</a>, <a href="https://arxiv.org/format/1706.00941">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> DANI: A Fast Diffusion Aware Network Inference Algorithm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ramezani%2C+M">Maryam Ramezani</a>, <a href="/search/cs?searchtype=author&query=Rabiee%2C+H+R">Hamid R. Rabiee</a>, <a href="/search/cs?searchtype=author&query=Tahani%2C+M">Maryam Tahani</a>, <a href="/search/cs?searchtype=author&query=Rajabi%2C+A">Arezoo Rajabi</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="1706.00941v1-abstract-short" style="display: inline;"> The fast growth of social networks and their privacy requirements in recent years, has lead to increasing difficulty in obtaining complete topology of these networks. However, diffusion information over these networks is available and many algorithms have been proposed to infer the underlying networks by using this information. The previously proposed algorithms only focus on inferring more links… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1706.00941v1-abstract-full').style.display = 'inline'; document.getElementById('1706.00941v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1706.00941v1-abstract-full" style="display: none;"> The fast growth of social networks and their privacy requirements in recent years, has lead to increasing difficulty in obtaining complete topology of these networks. However, diffusion information over these networks is available and many algorithms have been proposed to infer the underlying networks by using this information. The previously proposed algorithms only focus on inferring more links and do not pay attention to the important characteristics of the underlying social networks In this paper, we propose a novel algorithm, called DANI, to infer the underlying network structure while preserving its properties by using the diffusion information. Moreover, the running time of the proposed method is considerably lower than the previous methods. We applied the proposed method to both real and synthetic networks. The experimental results showed that DANI has higher accuracy and lower run time compared to well-known network inference methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1706.00941v1-abstract-full').style.display = 'none'; document.getElementById('1706.00941v1-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 June, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2017. </p> </li> </ol> <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