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 1–14 of 14 results for author: <span class="mathjax">Purcell, M</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=Purcell%2C+M">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="Purcell, M"> </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=Purcell%2C+M&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="Purcell, M"> <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/2410.09078">arXiv:2410.09078</a> <span> [<a href="https://arxiv.org/pdf/2410.09078">pdf</a>, <a href="https://arxiv.org/format/2410.09078">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Momcilovic%2C+T+B">Tomas Bueno Momcilovic</a>, <a href="/search/cs?searchtype=author&query=Balta%2C+D">Dian Balta</a>, <a href="/search/cs?searchtype=author&query=Buesser%2C+B">Beat Buesser</a>, <a href="/search/cs?searchtype=author&query=Zizzo%2C+G">Giulio Zizzo</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</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="2410.09078v1-abstract-short" style="display: inline;"> The EU AI Act (EUAIA) introduces requirements for AI systems which intersect with the processes required to establish adversarial robustness. However, given the ambiguous language of regulation and the dynamicity of adversarial attacks, developers of systems with highly complex models such as LLMs may find their effort to be duplicated without the assurance of having achieved either compliance or… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09078v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09078v1-abstract-full" style="display: none;"> The EU AI Act (EUAIA) introduces requirements for AI systems which intersect with the processes required to establish adversarial robustness. However, given the ambiguous language of regulation and the dynamicity of adversarial attacks, developers of systems with highly complex models such as LLMs may find their effort to be duplicated without the assurance of having achieved either compliance or robustness. This paper presents a functional architecture that focuses on bridging the two properties, by introducing components with clear reference to their source. Taking the detection layer recommended by the literature, and the reporting layer required by the law, we aim to support developers and auditors with a reasoning layer based on knowledge augmentation (rules, assurance cases, contextual mappings). Our findings demonstrate a novel direction for ensuring LLMs deployed in the EU are both compliant and adversarially robust, which underpin trustworthiness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09078v1-abstract-full').style.display = 'none'; document.getElementById('2410.09078v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in the VECOMP 2024 workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.07962">arXiv:2410.07962</a> <span> [<a href="https://arxiv.org/pdf/2410.07962">pdf</a>, <a href="https://arxiv.org/format/2410.07962">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Momcilovic%2C+T+B">Tomas Bueno Momcilovic</a>, <a href="/search/cs?searchtype=author&query=Buesser%2C+B">Beat Buesser</a>, <a href="/search/cs?searchtype=author&query=Zizzo%2C+G">Giulio Zizzo</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Balta%2C+D">Dian Balta</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="2410.07962v1-abstract-short" style="display: inline;"> Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an evolving combination of adversarial training and guardrails. However, managing the implicit and heterogeneous knowledge for continuously assuring robustness is diffi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07962v1-abstract-full').style.display = 'inline'; document.getElementById('2410.07962v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07962v1-abstract-full" style="display: none;"> Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an evolving combination of adversarial training and guardrails. However, managing the implicit and heterogeneous knowledge for continuously assuring robustness is difficult. We introduce a novel approach for assurance of the adversarial robustness of LLMs based on formal argumentation. Using ontologies for formalization, we structure state-of-the-art attacks and defenses, facilitating the creation of a human-readable assurance case, and a machine-readable representation. We demonstrate its application with examples in English language and code translation tasks, and provide implications for theory and practice, by targeting engineers, data scientists, users, and auditors. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07962v1-abstract-full').style.display = 'none'; document.getElementById('2410.07962v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 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">To be published in xAI 2024, late-breaking track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05306">arXiv:2410.05306</a> <span> [<a href="https://arxiv.org/pdf/2410.05306">pdf</a>, <a href="https://arxiv.org/format/2410.05306">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Momcilovic%2C+T+B">Tomas Bueno Momcilovic</a>, <a href="/search/cs?searchtype=author&query=Buesser%2C+B">Beat Buesser</a>, <a href="/search/cs?searchtype=author&query=Zizzo%2C+G">Giulio Zizzo</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Balta%2C+D">Dian Balta</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="2410.05306v1-abstract-short" style="display: inline;"> Large language models are prone to misuse and vulnerable to security threats, raising significant safety and security concerns. The European Union's Artificial Intelligence Act seeks to enforce AI robustness in certain contexts, but faces implementation challenges due to the lack of standards, complexity of LLMs and emerging security vulnerabilities. Our research introduces a framework using ontol… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05306v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05306v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05306v1-abstract-full" style="display: none;"> Large language models are prone to misuse and vulnerable to security threats, raising significant safety and security concerns. The European Union's Artificial Intelligence Act seeks to enforce AI robustness in certain contexts, but faces implementation challenges due to the lack of standards, complexity of LLMs and emerging security vulnerabilities. Our research introduces a framework using ontologies, assurance cases, and factsheets to support engineers and stakeholders in understanding and documenting AI system compliance and security regarding adversarial robustness. This approach aims to ensure that LLMs adhere to regulatory standards and are equipped to counter potential threats. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05306v1-abstract-full').style.display = 'none'; document.getElementById('2410.05306v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in the AI Act Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.05304">arXiv:2410.05304</a> <span> [<a href="https://arxiv.org/pdf/2410.05304">pdf</a>, <a href="https://arxiv.org/format/2410.05304">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="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Momcilovic%2C+T+B">Tomas Bueno Momcilovic</a>, <a href="/search/cs?searchtype=author&query=Balta%2C+D">Dian Balta</a>, <a href="/search/cs?searchtype=author&query=Buesser%2C+B">Beat Buesser</a>, <a href="/search/cs?searchtype=author&query=Zizzo%2C+G">Giulio Zizzo</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</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="2410.05304v1-abstract-short" style="display: inline;"> This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these models face, including adversarial attacks based on jailbreaking, heuristics, and randomization. We propose a layered framework incorporating guardrails at various s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05304v1-abstract-full').style.display = 'inline'; document.getElementById('2410.05304v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.05304v1-abstract-full" style="display: none;"> This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these models face, including adversarial attacks based on jailbreaking, heuristics, and randomization. We propose a layered framework incorporating guardrails at various stages of LLM deployment, aimed at mitigating these attacks and ensuring compliance with the EU AI Act. Our approach includes a meta-layer for dynamic risk management and reasoning, crucial for addressing the evolving nature of LLM vulnerabilities. We illustrate our method with two exemplary assurance cases, highlighting how different contexts demand tailored strategies to ensure robust and compliant AI systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.05304v1-abstract-full').style.display = 'none'; document.getElementById('2410.05304v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to the ASSURE 2024 workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17699">arXiv:2409.17699</a> <span> [<a href="https://arxiv.org/pdf/2409.17699">pdf</a>, <a href="https://arxiv.org/format/2409.17699">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"> MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cornacchia%2C+G">Giandomenico Cornacchia</a>, <a href="/search/cs?searchtype=author&query=Zizzo%2C+G">Giulio Zizzo</a>, <a href="/search/cs?searchtype=author&query=Fraser%2C+K">Kieran Fraser</a>, <a href="/search/cs?searchtype=author&query=Hameed%2C+M+Z">Muhammad Zaid Hameed</a>, <a href="/search/cs?searchtype=author&query=Rawat%2C+A">Ambrish Rawat</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17699v3-abstract-short" style="display: inline;"> The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLMs, endanger data integrity and user privacy. Guardrails serve as crucial protective mechanisms against such threats, but existing models often fall short in terms of both detection… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17699v3-abstract-full').style.display = 'inline'; document.getElementById('2409.17699v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17699v3-abstract-full" style="display: none;"> The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLMs, endanger data integrity and user privacy. Guardrails serve as crucial protective mechanisms against such threats, but existing models often fall short in terms of both detection accuracy, and computational efficiency. This paper advocates for the significance of jailbreak attack prevention on LLMs, and emphasises the role of input guardrails in safeguarding these models. We introduce MoJE (Mixture of Jailbreak Expert), a novel guardrail architecture designed to surpass current limitations in existing state-of-the-art guardrails. By employing simple linguistic statistical techniques, MoJE excels in detecting jailbreak attacks while maintaining minimal computational overhead during model inference. Through rigorous experimentation, MoJE demonstrates superior performance capable of detecting 90% of the attacks without compromising benign prompts, enhancing LLMs security against jailbreak attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17699v3-abstract-full').style.display = 'none'; document.getElementById('2409.17699v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.15398">arXiv:2409.15398</a> <span> [<a href="https://arxiv.org/pdf/2409.15398">pdf</a>, <a href="https://arxiv.org/format/2409.15398">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"> Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rawat%2C+A">Ambrish Rawat</a>, <a href="/search/cs?searchtype=author&query=Schoepf%2C+S">Stefan Schoepf</a>, <a href="/search/cs?searchtype=author&query=Zizzo%2C+G">Giulio Zizzo</a>, <a href="/search/cs?searchtype=author&query=Cornacchia%2C+G">Giandomenico Cornacchia</a>, <a href="/search/cs?searchtype=author&query=Hameed%2C+M+Z">Muhammad Zaid Hameed</a>, <a href="/search/cs?searchtype=author&query=Fraser%2C+K">Kieran Fraser</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Buesser%2C+B">Beat Buesser</a>, <a href="/search/cs?searchtype=author&query=Daly%2C+E+M">Elizabeth M. Daly</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Sattigeri%2C+P">Prasanna Sattigeri</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Pin-Yu Chen</a>, <a href="/search/cs?searchtype=author&query=Varshney%2C+K+R">Kush R. Varshney</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.15398v1-abstract-short" style="display: inline;"> As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15398v1-abstract-full').style.display = 'inline'; document.getElementById('2409.15398v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15398v1-abstract-full" style="display: none;"> As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversarial attacks. Despite growing academic interest in adversarial risks for generative AI, there is limited guidance tailored for practitioners to assess and mitigate these challenges in real-world environments. To address this, our contributions include: (1) a practical examination of red- and blue-teaming strategies for securing generative AI, (2) identification of key challenges and open questions in defense development and evaluation, and (3) the Attack Atlas, an intuitive framework that brings a practical approach to analyzing single-turn input attacks, placing it at the forefront for practitioners. This work aims to bridge the gap between academic insights and practical security measures for the protection of generative AI systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15398v1-abstract-full').style.display = 'none'; document.getElementById('2409.15398v1-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> 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.19304">arXiv:2310.19304</a> <span> [<a href="https://arxiv.org/pdf/2310.19304">pdf</a>, <a href="https://arxiv.org/format/2310.19304">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"> Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kadhe%2C+S+R">Swanand Ravindra Kadhe</a>, <a href="/search/cs?searchtype=author&query=Ludwig%2C+H">Heiko Ludwig</a>, <a href="/search/cs?searchtype=author&query=Baracaldo%2C+N">Nathalie Baracaldo</a>, <a href="/search/cs?searchtype=author&query=King%2C+A">Alan King</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yi Zhou</a>, <a href="/search/cs?searchtype=author&query=Houck%2C+K">Keith Houck</a>, <a href="/search/cs?searchtype=author&query=Rawat%2C+A">Ambrish Rawat</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Holohan%2C+N">Naoise Holohan</a>, <a href="/search/cs?searchtype=author&query=Takeuchi%2C+M">Mikio Takeuchi</a>, <a href="/search/cs?searchtype=author&query=Kawahara%2C+R">Ryo Kawahara</a>, <a href="/search/cs?searchtype=author&query=Drucker%2C+N">Nir Drucker</a>, <a href="/search/cs?searchtype=author&query=Shaul%2C+H">Hayim Shaul</a>, <a href="/search/cs?searchtype=author&query=Kushnir%2C+E">Eyal Kushnir</a>, <a href="/search/cs?searchtype=author&query=Soceanu%2C+O">Omri Soceanu</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="2310.19304v1-abstract-short" style="display: inline;"> The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and its partner banks. Trust among these financial institutions is limited by regulation and competition. Federated learning (FL) enables entities to collaboratively train a model when data is either vertically or horizontal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.19304v1-abstract-full').style.display = 'inline'; document.getElementById('2310.19304v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.19304v1-abstract-full" style="display: none;"> The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and its partner banks. Trust among these financial institutions is limited by regulation and competition. Federated learning (FL) enables entities to collaboratively train a model when data is either vertically or horizontally partitioned across the entities. However, in real-world financial anomaly detection scenarios, the data is partitioned both vertically and horizontally and hence it is not possible to use existing FL approaches in a plug-and-play manner. Our novel solution, PV4FAD, combines fully homomorphic encryption (HE), secure multi-party computation (SMPC), differential privacy (DP), and randomization techniques to balance privacy and accuracy during training and to prevent inference threats at model deployment time. Our solution provides input privacy through HE and SMPC, and output privacy against inference time attacks through DP. Specifically, we show that, in the honest-but-curious threat model, banks do not learn any sensitive features about PNS transactions, and the PNS does not learn any information about the banks' dataset but only learns prediction labels. We also develop and analyze a DP mechanism to protect output privacy during inference. Our solution generates high-utility models by significantly reducing the per-bank noise level while satisfying distributed DP. To ensure high accuracy, our approach produces an ensemble model, in particular, a random forest. This enables us to take advantage of the well-known properties of ensembles to reduce variance and increase accuracy. Our solution won second prize in the first phase of the U.S. Privacy Enhancing Technologies (PETs) Prize Challenge. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.19304v1-abstract-full').style.display = 'none'; document.getElementById('2310.19304v1-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> 30 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">Prize Winner in the U.S. Privacy Enhancing Technologies (PETs) Prize Challenge</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.08125">arXiv:2208.08125</a> <span> [<a href="https://arxiv.org/pdf/2208.08125">pdf</a>, <a href="https://arxiv.org/format/2208.08125">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> </div> </div> <p class="title is-5 mathjax"> A Tutorial Introduction to Lattice-based Cryptography and Homomorphic Encryption </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yang Li</a>, <a href="/search/cs?searchtype=author&query=Ng%2C+K+S">Kee Siong Ng</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Michael Purcell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2208.08125v2-abstract-short" style="display: inline;"> Why study Lattice-based Cryptography? There are a few ways to answer this question. 1. It is useful to have cryptosystems that are based on a variety of hard computational problems so the different cryptosystems are not all vulnerable in the same way. 2. The computational aspects of lattice-based cryptosystem are usually simple to understand and fairly easy to implement in practice. 3. Lattice-bas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.08125v2-abstract-full').style.display = 'inline'; document.getElementById('2208.08125v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.08125v2-abstract-full" style="display: none;"> Why study Lattice-based Cryptography? There are a few ways to answer this question. 1. It is useful to have cryptosystems that are based on a variety of hard computational problems so the different cryptosystems are not all vulnerable in the same way. 2. The computational aspects of lattice-based cryptosystem are usually simple to understand and fairly easy to implement in practice. 3. Lattice-based cryptosystems have lower encryption/decryption computational complexities compared to popular cryptosystems that are based on the integer factorisation or the discrete logarithm problems. 4. Lattice-based cryptosystems enjoy strong worst-case hardness security proofs based on approximate versions of known NP-hard lattice problems. 5. Lattice-based cryptosystems are believed to be good candidates for post-quantum cryptography, since there are currently no known quantum algorithms for solving lattice problems that perform significantly better than the best-known classical (non-quantum) algorithms, unlike for integer factorisation and (elliptic curve) discrete logarithm problems. 6. Last but not least, interesting structures in lattice problems have led to significant advances in Homomorphic Encryption, a new research area with wide-ranging applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.08125v2-abstract-full').style.display = 'none'; document.getElementById('2208.08125v2-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.12163">arXiv:2203.12163</a> <span> [<a href="https://arxiv.org/pdf/2203.12163">pdf</a>, <a href="https://arxiv.org/format/2203.12163">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Adaptive Aggregation For Federated Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jayaram%2C+K+R">K. R. Jayaram</a>, <a href="/search/cs?searchtype=author&query=Muthusamy%2C+V">Vinod Muthusamy</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+G">Gegi Thomas</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+A">Ashish Verma</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</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="2203.12163v2-abstract-short" style="display: inline;"> Advances in federated learning (FL) algorithms,along with technologies like differential privacy and homomorphic encryption, have led to FL being increasingly adopted and used in many application domains. This increasing adoption has led to rapid growth in the number, size (number of participants/parties) and diversity (intermittent vs. active parties) of FL jobs. Many existing FL systems, based o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.12163v2-abstract-full').style.display = 'inline'; document.getElementById('2203.12163v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.12163v2-abstract-full" style="display: none;"> Advances in federated learning (FL) algorithms,along with technologies like differential privacy and homomorphic encryption, have led to FL being increasingly adopted and used in many application domains. This increasing adoption has led to rapid growth in the number, size (number of participants/parties) and diversity (intermittent vs. active parties) of FL jobs. Many existing FL systems, based on centralized (often single) model aggregators are unable to scale to handle large FL jobs and adapt to parties' behavior. In this paper, we present a new scalable and adaptive architecture for FL aggregation. First, we demonstrate how traditional tree overlay based aggregation techniques (from P2P, publish-subscribe and stream processing research) can help FL aggregation scale, but are ineffective from a resource utilization and cost standpoint. Next, we present the design and implementation of AdaFed, which uses serverless/cloud functions to adaptively scale aggregation in a resource efficient and fault tolerant manner. We describe how AdaFed enables FL aggregation to be dynamically deployed only when necessary, elastically scaled to handle participant joins/leaves and is fault tolerant with minimal effort required on the (aggregation) programmer side. We also demonstrate that our prototype based on Ray scales to thousands of participants, and is able to achieve a >90% reduction in resource requirements and cost, with minimal impact on aggregation latency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.12163v2-abstract-full').style.display = 'none'; document.getElementById('2203.12163v2-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> 6 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 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">ACM Class:</span> C.2.4; C.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.12443">arXiv:2202.12443</a> <span> [<a href="https://arxiv.org/pdf/2202.12443">pdf</a>, <a href="https://arxiv.org/format/2202.12443">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baracaldo%2C+N">Nathalie Baracaldo</a>, <a href="/search/cs?searchtype=author&query=Anwar%2C+A">Ali Anwar</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Rawat%2C+A">Ambrish Rawat</a>, <a href="/search/cs?searchtype=author&query=Sinn%2C+M">Mathieu Sinn</a>, <a href="/search/cs?searchtype=author&query=Altakrouri%2C+B">Bashar Altakrouri</a>, <a href="/search/cs?searchtype=author&query=Balta%2C+D">Dian Balta</a>, <a href="/search/cs?searchtype=author&query=Sellami%2C+M">Mahdi Sellami</a>, <a href="/search/cs?searchtype=author&query=Kuhn%2C+P">Peter Kuhn</a>, <a href="/search/cs?searchtype=author&query=Schopp%2C+U">Ulrich Schopp</a>, <a href="/search/cs?searchtype=author&query=Buchinger%2C+M">Matthias Buchinger</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2202.12443v1-abstract-short" style="display: inline;"> Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data. With respect to ethical guidelines, FL is promising regarding privacy, but needs to excel vis-脿-vis transparency and trustworthiness. In particular, FL has to address the accountability of the parties involved and their adherence to rules, law and principles. We introduce AF^2 Fra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12443v1-abstract-full').style.display = 'inline'; document.getElementById('2202.12443v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.12443v1-abstract-full" style="display: none;"> Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data. With respect to ethical guidelines, FL is promising regarding privacy, but needs to excel vis-脿-vis transparency and trustworthiness. In particular, FL has to address the accountability of the parties involved and their adherence to rules, law and principles. We introduce AF^2 Framework, where we instrument FL with accountability by fusing verifiable claims with tamper-evident facts, into reproducible arguments. We build on AI FactSheets for instilling transparency and trustworthiness into the AI lifecycle and expand it to incorporate dynamic and nested facts, as well as complex model compositions in FL. Based on our approach, an auditor can validate, reproduce and certify a FL process. This can be directly applied in practice to address the challenges of AI engineering and ethics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12443v1-abstract-full').style.display = 'none'; document.getElementById('2202.12443v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> <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, 4 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.04245">arXiv:2107.04245</a> <span> [<a href="https://arxiv.org/pdf/2107.04245">pdf</a>, <a href="https://arxiv.org/ps/2107.04245">ps</a>, <a href="https://arxiv.org/format/2107.04245">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> </div> </div> <p class="title is-5 mathjax"> Private Graph Data Release: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yang Li</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Michael Purcell</a>, <a href="/search/cs?searchtype=author&query=Rakotoarivelo%2C+T">Thierry Rakotoarivelo</a>, <a href="/search/cs?searchtype=author&query=Smith%2C+D">David Smith</a>, <a href="/search/cs?searchtype=author&query=Ranbaduge%2C+T">Thilina Ranbaduge</a>, <a href="/search/cs?searchtype=author&query=Ng%2C+K+S">Kee Siong Ng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2107.04245v2-abstract-short" style="display: inline;"> The application of graph analytics to various domains has yielded tremendous societal and economical benefits in recent years. However, the increasingly widespread adoption of graph analytics comes with a commensurate increase in the need to protect private information in graph data, especially in light of the many privacy breaches in real-world graph data that was supposed to preserve sensitive i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.04245v2-abstract-full').style.display = 'inline'; document.getElementById('2107.04245v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.04245v2-abstract-full" style="display: none;"> The application of graph analytics to various domains has yielded tremendous societal and economical benefits in recent years. However, the increasingly widespread adoption of graph analytics comes with a commensurate increase in the need to protect private information in graph data, especially in light of the many privacy breaches in real-world graph data that was supposed to preserve sensitive information. This paper provides a comprehensive survey of private graph data release algorithms that seek to achieve the fine balance between privacy and utility, with a specific focus on provably private mechanisms. Many of these mechanisms are natural extensions of the Differential Privacy framework to graph data, but we also investigate more general privacy formulations like Pufferfish Privacy that address some of the limitations of Differential Privacy. We also provide a wide-ranging survey of the applications of private graph data release mechanisms to social networks, finance, supply chain, and health care. This survey paper and the taxonomy it provides should benefit practitioners and researchers alike in the increasingly important area of private analytics and data release. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.04245v2-abstract-full').style.display = 'none'; document.getElementById('2107.04245v2-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.07248">arXiv:2103.07248</a> <span> [<a href="https://arxiv.org/pdf/2103.07248">pdf</a>, <a href="https://arxiv.org/format/2103.07248">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="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Knowledge- and Data-driven Services for Energy Systems using Graph Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fusco%2C+F">Francesco Fusco</a>, <a href="/search/cs?searchtype=author&query=Eck%2C+B">Bradley Eck</a>, <a href="/search/cs?searchtype=author&query=Gormally%2C+R">Robert Gormally</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Tirupathi%2C+S">Seshu Tirupathi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.07248v1-abstract-short" style="display: inline;"> The transition away from carbon-based energy sources poses several challenges for the operation of electricity distribution systems. Increasing shares of distributed energy resources (e.g. renewable energy generators, electric vehicles) and internet-connected sensing and control devices (e.g. smart heating and cooling) require new tools to support accurate, datadriven decision making. Modelling th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.07248v1-abstract-full').style.display = 'inline'; document.getElementById('2103.07248v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.07248v1-abstract-full" style="display: none;"> The transition away from carbon-based energy sources poses several challenges for the operation of electricity distribution systems. Increasing shares of distributed energy resources (e.g. renewable energy generators, electric vehicles) and internet-connected sensing and control devices (e.g. smart heating and cooling) require new tools to support accurate, datadriven decision making. Modelling the effect of such growing complexity in the electrical grid is possible in principle using state-of-the-art power-power flow models. In practice, the detailed information needed for these physical simulations may be unknown or prohibitively expensive to obtain. Hence, datadriven approaches to power systems modelling, including feedforward neural networks and auto-encoders, have been studied to leverage the increasing availability of sensor data, but have seen limited practical adoption due to lack of transparency and inefficiencies on large-scale problems. Our work addresses this gap by proposing a data- and knowledge-driven probabilistic graphical model for energy systems based on the framework of graph neural networks (GNNs). The model can explicitly factor in domain knowledge, in the form of grid topology or physics constraints, thus resulting in sparser architectures and much smaller parameters dimensionality when compared with traditional machine-learning models with similar accuracy. Results obtained from a real-world smart-grid demonstration project show how the GNN was used to inform grid congestion predictions and market bidding services for a distribution system operator participating in an energy flexibility market. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.07248v1-abstract-full').style.display = 'none'; document.getElementById('2103.07248v1-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 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication in proceedings of IEEE Conference of Big Data 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/2007.10987">arXiv:2007.10987</a> <span> [<a href="https://arxiv.org/pdf/2007.10987">pdf</a>, <a href="https://arxiv.org/format/2007.10987">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> IBM Federated Learning: an Enterprise Framework White Paper V0.1 </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ludwig%2C+H">Heiko Ludwig</a>, <a href="/search/cs?searchtype=author&query=Baracaldo%2C+N">Nathalie Baracaldo</a>, <a href="/search/cs?searchtype=author&query=Thomas%2C+G">Gegi Thomas</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yi Zhou</a>, <a href="/search/cs?searchtype=author&query=Anwar%2C+A">Ali Anwar</a>, <a href="/search/cs?searchtype=author&query=Rajamoni%2C+S">Shashank Rajamoni</a>, <a href="/search/cs?searchtype=author&query=Ong%2C+Y">Yuya Ong</a>, <a href="/search/cs?searchtype=author&query=Radhakrishnan%2C+J">Jayaram Radhakrishnan</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+A">Ashish Verma</a>, <a href="/search/cs?searchtype=author&query=Sinn%2C+M">Mathieu Sinn</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Rawat%2C+A">Ambrish Rawat</a>, <a href="/search/cs?searchtype=author&query=Minh%2C+T">Tran Minh</a>, <a href="/search/cs?searchtype=author&query=Holohan%2C+N">Naoise Holohan</a>, <a href="/search/cs?searchtype=author&query=Chakraborty%2C+S">Supriyo Chakraborty</a>, <a href="/search/cs?searchtype=author&query=Whitherspoon%2C+S">Shalisha Whitherspoon</a>, <a href="/search/cs?searchtype=author&query=Steuer%2C+D">Dean Steuer</a>, <a href="/search/cs?searchtype=author&query=Wynter%2C+L">Laura Wynter</a>, <a href="/search/cs?searchtype=author&query=Hassan%2C+H">Hifaz Hassan</a>, <a href="/search/cs?searchtype=author&query=Laguna%2C+S">Sean Laguna</a>, <a href="/search/cs?searchtype=author&query=Yurochkin%2C+M">Mikhail Yurochkin</a>, <a href="/search/cs?searchtype=author&query=Agarwal%2C+M">Mayank Agarwal</a>, <a href="/search/cs?searchtype=author&query=Chuba%2C+E">Ebube Chuba</a>, <a href="/search/cs?searchtype=author&query=Abay%2C+A">Annie Abay</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="2007.10987v1-abstract-short" style="display: inline;"> Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume. However, solving federated machine learning problems raises issues above and beyond those of centralized machine learning. These issues include setting up communication infrastructure between parties, coordinating the learn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.10987v1-abstract-full').style.display = 'inline'; document.getElementById('2007.10987v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.10987v1-abstract-full" style="display: none;"> Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume. However, solving federated machine learning problems raises issues above and beyond those of centralized machine learning. These issues include setting up communication infrastructure between parties, coordinating the learning process, integrating party results, understanding the characteristics of the training data sets of different participating parties, handling data heterogeneity, and operating with the absence of a verification data set. IBM Federated Learning provides infrastructure and coordination for federated learning. Data scientists can design and run federated learning jobs based on existing, centralized machine learning models and can provide high-level instructions on how to run the federation. The framework applies to both Deep Neural Networks as well as ``traditional'' approaches for the most common machine learning libraries. {\proj} enables data scientists to expand their scope from centralized to federated machine learning, minimizing the learning curve at the outset while also providing the flexibility to deploy to different compute environments and design custom fusion algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.10987v1-abstract-full').style.display = 'none'; document.getElementById('2007.10987v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 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">17 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.6; I.2.11 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2003.12141">arXiv:2003.12141</a> <span> [<a href="https://arxiv.org/pdf/2003.12141">pdf</a>, <a href="https://arxiv.org/format/2003.12141">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <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="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Scalable Deployment of AI Time-series Models for IoT </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eck%2C+B">Bradley Eck</a>, <a href="/search/cs?searchtype=author&query=Fusco%2C+F">Francesco Fusco</a>, <a href="/search/cs?searchtype=author&query=Gormally%2C+R">Robert Gormally</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Tirupathi%2C+S">Seshu Tirupathi</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="2003.12141v1-abstract-short" style="display: inline;"> IBM Research Castor, a cloud-native system for managing and deploying large numbers of AI time-series models in IoT applications, is described. Modelling code templates, in Python and R, following a typical machine-learning workflow are supported. A knowledge-based approach to managing model and time-series data allows the use of general semantic concepts for expressing feature engineering tasks.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.12141v1-abstract-full').style.display = 'inline'; document.getElementById('2003.12141v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2003.12141v1-abstract-full" style="display: none;"> IBM Research Castor, a cloud-native system for managing and deploying large numbers of AI time-series models in IoT applications, is described. Modelling code templates, in Python and R, following a typical machine-learning workflow are supported. A knowledge-based approach to managing model and time-series data allows the use of general semantic concepts for expressing feature engineering tasks. Model templates can be programmatically deployed against specific instances of semantic concepts, thus supporting model reuse and automated replication as the IoT application grows. Deployed models are automatically executed in parallel leveraging a serverless cloud computing framework. The complete history of trained model versions and rolling-horizon predictions is persisted, thus enabling full model lineage and traceability. Results from deployments in real-world smart-grid live forecasting applications are reported. Scalability of executing up to tens of thousands of AI modelling tasks is also evaluated. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.12141v1-abstract-full').style.display = 'none'; document.getElementById('2003.12141v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Workshop AI for Internet of Things, IJCAI 2019 </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