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 1–18 of 18 results for author: <span class="mathjax">Miehling, E</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=Miehling%2C+E">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="Miehling, E"> </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=Miehling%2C+E&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="Miehling, E"> <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/2412.07724">arXiv:2412.07724</a> <span> [<a href="https://arxiv.org/pdf/2412.07724">pdf</a>, <a href="https://arxiv.org/format/2412.07724">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Granite Guardian </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Padhi%2C+I">Inkit Padhi</a>, <a href="/search/cs?searchtype=author&query=Nagireddy%2C+M">Manish Nagireddy</a>, <a href="/search/cs?searchtype=author&query=Cornacchia%2C+G">Giandomenico Cornacchia</a>, <a href="/search/cs?searchtype=author&query=Chaudhury%2C+S">Subhajit Chaudhury</a>, <a href="/search/cs?searchtype=author&query=Pedapati%2C+T">Tejaswini Pedapati</a>, <a href="/search/cs?searchtype=author&query=Dognin%2C+P">Pierre Dognin</a>, <a href="/search/cs?searchtype=author&query=Murugesan%2C+K">Keerthiram Murugesan</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Cooper%2C+M+S">Mart铆n Santill谩n Cooper</a>, <a href="/search/cs?searchtype=author&query=Fraser%2C+K">Kieran Fraser</a>, <a href="/search/cs?searchtype=author&query=Zizzo%2C+G">Giulio Zizzo</a>, <a href="/search/cs?searchtype=author&query=Hameed%2C+M+Z">Muhammad Zaid Hameed</a>, <a href="/search/cs?searchtype=author&query=Purcell%2C+M">Mark Purcell</a>, <a href="/search/cs?searchtype=author&query=Desmond%2C+M">Michael Desmond</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+Q">Qian Pan</a>, <a href="/search/cs?searchtype=author&query=Ashktorab%2C+Z">Zahra Ashktorab</a>, <a href="/search/cs?searchtype=author&query=Vejsbjerg%2C+I">Inge Vejsbjerg</a>, <a href="/search/cs?searchtype=author&query=Daly%2C+E+M">Elizabeth M. Daly</a>, <a href="/search/cs?searchtype=author&query=Hind%2C+M">Michael Hind</a>, <a href="/search/cs?searchtype=author&query=Geyer%2C+W">Werner Geyer</a>, <a href="/search/cs?searchtype=author&query=Rawat%2C+A">Ambrish Rawat</a>, <a href="/search/cs?searchtype=author&query=Varshney%2C+K+R">Kush R. Varshney</a>, <a href="/search/cs?searchtype=author&query=Sattigeri%2C+P">Prasanna Sattigeri</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="2412.07724v2-abstract-short" style="display: inline;"> We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM). These models offer comprehensive coverage across multiple risk dimensions, including social bias, profanity, violence, sexual content, unethical behavior, jailbreaking, and hallucination-r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07724v2-abstract-full').style.display = 'inline'; document.getElementById('2412.07724v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.07724v2-abstract-full" style="display: none;"> We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM). These models offer comprehensive coverage across multiple risk dimensions, including social bias, profanity, violence, sexual content, unethical behavior, jailbreaking, and hallucination-related risks such as context relevance, groundedness, and answer relevance for retrieval-augmented generation (RAG). Trained on a unique dataset combining human annotations from diverse sources and synthetic data, Granite Guardian models address risks typically overlooked by traditional risk detection models, such as jailbreaks and RAG-specific issues. With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space. Released as open-source, Granite Guardian aims to promote responsible AI development across the community. https://github.com/ibm-granite/granite-guardian <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.07724v2-abstract-full').style.display = 'none'; document.getElementById('2412.07724v2-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12405">arXiv:2411.12405</a> <span> [<a href="https://arxiv.org/pdf/2411.12405">pdf</a>, <a href="https://arxiv.org/format/2411.12405">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Evaluating the Prompt Steerability of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Desmond%2C+M">Michael Desmond</a>, <a href="/search/cs?searchtype=author&query=Ramamurthy%2C+K+N">Karthikeyan Natesan Ramamurthy</a>, <a href="/search/cs?searchtype=author&query=Daly%2C+E+M">Elizabeth M. Daly</a>, <a href="/search/cs?searchtype=author&query=Dognin%2C+P">Pierre Dognin</a>, <a href="/search/cs?searchtype=author&query=Rios%2C+J">Jesus Rios</a>, <a href="/search/cs?searchtype=author&query=Bouneffouf%2C+D">Djallel Bouneffouf</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+M">Miao Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.12405v1-abstract-short" style="display: inline;"> Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark for evaluating the steerability of model personas as a function of prompting. Our design is based on… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12405v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12405v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12405v1-abstract-full" style="display: none;"> Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark for evaluating the steerability of model personas as a function of prompting. Our design is based on a formal definition of prompt steerability, which analyzes the degree to which a model's joint behavioral distribution can be shifted from its baseline behavior. By defining steerability indices and inspecting how these indices change as a function of steering effort, we can estimate the steerability of a model across various persona dimensions and directions. Our benchmark reveals that the steerability of many current models is limited -- due to both a skew in their baseline behavior and an asymmetry in their steerability across many persona dimensions. We release an implementation of our benchmark at https://github.com/IBM/prompt-steering. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12405v1-abstract-full').style.display = 'none'; document.getElementById('2411.12405v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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/2409.05907">arXiv:2409.05907</a> <span> [<a href="https://arxiv.org/pdf/2409.05907">pdf</a>, <a href="https://arxiv.org/format/2409.05907">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Programming Refusal with Conditional Activation Steering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lee%2C+B+W">Bruce W. Lee</a>, <a href="/search/cs?searchtype=author&query=Padhi%2C+I">Inkit Padhi</a>, <a href="/search/cs?searchtype=author&query=Ramamurthy%2C+K+N">Karthikeyan Natesan Ramamurthy</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Dognin%2C+P">Pierre Dognin</a>, <a href="/search/cs?searchtype=author&query=Nagireddy%2C+M">Manish Nagireddy</a>, <a href="/search/cs?searchtype=author&query=Dhurandhar%2C+A">Amit Dhurandhar</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="2409.05907v2-abstract-short" style="display: inline;"> LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selective responses are essential, such as content moderation or domain-specific assistants. In this paper, we propose Conditional Activation Steering (CAST)… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05907v2-abstract-full').style.display = 'inline'; document.getElementById('2409.05907v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.05907v2-abstract-full" style="display: none;"> LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selective responses are essential, such as content moderation or domain-specific assistants. In this paper, we propose Conditional Activation Steering (CAST), which analyzes LLM activation patterns during inference to selectively apply or withhold activation steering based on the input context. Our method is based on the observation that different categories of prompts activate distinct patterns in the model's hidden states. Using CAST, one can systematically control LLM behavior with rules like "if input is about hate speech or adult content, then refuse" or "if input is not about legal advice, then refuse." This allows for selective modification of responses to specific content while maintaining normal responses to other content, all without requiring weight optimization. We release an open-source implementation of our framework at <github.com/IBM/activation-steering>. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05907v2-abstract-full').style.display = 'none'; document.getElementById('2409.05907v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR 2025, Spotlight</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.11785">arXiv:2406.11785</a> <span> [<a href="https://arxiv.org/pdf/2406.11785">pdf</a>, <a href="https://arxiv.org/format/2406.11785">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> CELL your Model: Contrastive Explanations for Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luss%2C+R">Ronny Luss</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Dhurandhar%2C+A">Amit Dhurandhar</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="2406.11785v2-abstract-short" style="display: inline;"> The advent of black-box deep neural network classification models has sparked the need to explain their decisions. However, in the case of generative AI, such as large language models (LLMs), there is no class prediction to explain. Rather, one can ask why an LLM output a particular response to a given prompt. In this paper, we answer this question by proposing, to the best of our knowledge, the f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11785v2-abstract-full').style.display = 'inline'; document.getElementById('2406.11785v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.11785v2-abstract-full" style="display: none;"> The advent of black-box deep neural network classification models has sparked the need to explain their decisions. However, in the case of generative AI, such as large language models (LLMs), there is no class prediction to explain. Rather, one can ask why an LLM output a particular response to a given prompt. In this paper, we answer this question by proposing, to the best of our knowledge, the first contrastive explanation methods requiring simply black-box/query access. Our explanations suggest that an LLM outputs a reply to a given prompt because if the prompt was slightly modified, the LLM would have given a different response that is either less preferable or contradicts the original response. The key insight is that contrastive explanations simply require a scoring function that has meaning to the user and not necessarily a specific real valued quantity (viz. class label). We offer two algorithms for finding contrastive explanations: i) A myopic algorithm, which although effective in creating contrasts, requires many model calls and ii) A budgeted algorithm, our main algorithmic contribution, which intelligently creates contrasts adhering to a query budget, necessary for longer contexts. We show the efficacy of these methods on diverse natural language tasks such as open-text generation, automated red teaming, and explaining conversational degradation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.11785v2-abstract-full').style.display = 'none'; document.getElementById('2406.11785v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 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/2403.15115">arXiv:2403.15115</a> <span> [<a href="https://arxiv.org/pdf/2403.15115">pdf</a>, <a href="https://arxiv.org/format/2403.15115">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Language Models in Dialogue: Conversational Maxims for Human-AI Interactions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Nagireddy%2C+M">Manish Nagireddy</a>, <a href="/search/cs?searchtype=author&query=Sattigeri%2C+P">Prasanna Sattigeri</a>, <a href="/search/cs?searchtype=author&query=Daly%2C+E+M">Elizabeth M. Daly</a>, <a href="/search/cs?searchtype=author&query=Piorkowski%2C+D">David Piorkowski</a>, <a href="/search/cs?searchtype=author&query=Richards%2C+J+T">John T. Richards</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.15115v2-abstract-short" style="display: inline;"> Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings. We claim that many of the observed shortcomings can be attributed to violation of one or more conversational principles. By drawing upon extensive research from both the social science and AI communities, we propose a set of maxims -- quantity, quality, relevance, manner, benev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15115v2-abstract-full').style.display = 'inline'; document.getElementById('2403.15115v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.15115v2-abstract-full" style="display: none;"> Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings. We claim that many of the observed shortcomings can be attributed to violation of one or more conversational principles. By drawing upon extensive research from both the social science and AI communities, we propose a set of maxims -- quantity, quality, relevance, manner, benevolence, and transparency -- for describing effective human-AI conversation. We first justify the applicability of the first four maxims (from Grice) in the context of human-AI interactions. We then argue that two new maxims, benevolence (concerning the generation of, and engagement with, harmful content) and transparency (concerning recognition of one's knowledge boundaries, operational constraints, and intents), are necessary for addressing behavior unique to modern human-AI interactions. We evaluate the degree to which various language models are able to understand these maxims and find that models possess an internal prioritization of principles that can significantly impact their ability to interpret the maxims accurately. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.15115v2-abstract-full').style.display = 'none'; document.getElementById('2403.15115v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.06009">arXiv:2403.06009</a> <span> [<a href="https://arxiv.org/pdf/2403.06009">pdf</a>, <a href="https://arxiv.org/format/2403.06009">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"> Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Achintalwar%2C+S">Swapnaja Achintalwar</a>, <a href="/search/cs?searchtype=author&query=Garcia%2C+A+A">Adriana Alvarado Garcia</a>, <a href="/search/cs?searchtype=author&query=Anaby-Tavor%2C+A">Ateret Anaby-Tavor</a>, <a href="/search/cs?searchtype=author&query=Baldini%2C+I">Ioana Baldini</a>, <a href="/search/cs?searchtype=author&query=Berger%2C+S+E">Sara E. Berger</a>, <a href="/search/cs?searchtype=author&query=Bhattacharjee%2C+B">Bishwaranjan Bhattacharjee</a>, <a href="/search/cs?searchtype=author&query=Bouneffouf%2C+D">Djallel Bouneffouf</a>, <a href="/search/cs?searchtype=author&query=Chaudhury%2C+S">Subhajit Chaudhury</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Pin-Yu Chen</a>, <a href="/search/cs?searchtype=author&query=Chiazor%2C+L">Lamogha Chiazor</a>, <a href="/search/cs?searchtype=author&query=Daly%2C+E+M">Elizabeth M. Daly</a>, <a href="/search/cs?searchtype=author&query=DB%2C+K">Kirushikesh DB</a>, <a href="/search/cs?searchtype=author&query=de+Paula%2C+R+A">Rog茅rio Abreu de Paula</a>, <a href="/search/cs?searchtype=author&query=Dognin%2C+P">Pierre Dognin</a>, <a href="/search/cs?searchtype=author&query=Farchi%2C+E">Eitan Farchi</a>, <a href="/search/cs?searchtype=author&query=Ghosh%2C+S">Soumya Ghosh</a>, <a href="/search/cs?searchtype=author&query=Hind%2C+M">Michael Hind</a>, <a href="/search/cs?searchtype=author&query=Horesh%2C+R">Raya Horesh</a>, <a href="/search/cs?searchtype=author&query=Kour%2C+G">George Kour</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+J+Y">Ja Young Lee</a>, <a href="/search/cs?searchtype=author&query=Madaan%2C+N">Nishtha Madaan</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+S">Sameep Mehta</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Murugesan%2C+K">Keerthiram Murugesan</a>, <a href="/search/cs?searchtype=author&query=Nagireddy%2C+M">Manish Nagireddy</a> , et al. (13 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.06009v3-abstract-short" style="display: inline;"> Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we presen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06009v3-abstract-full').style.display = 'inline'; document.getElementById('2403.06009v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.06009v3-abstract-full" style="display: none;"> Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06009v3-abstract-full').style.display = 'none'; document.getElementById('2403.06009v3-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2206.02222">arXiv:2206.02222</a> <span> [<a href="https://arxiv.org/pdf/2206.02222">pdf</a>, <a href="https://arxiv.org/format/2206.02222">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</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"> How does a Rational Agent Act in an Epidemic? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Olmez%2C+S+Y">S. Yagiz Olmez</a>, <a href="/search/cs?searchtype=author&query=Aggarwal%2C+S">Shubham Aggarwal</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J+W">Jin Won Kim</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</a>, <a href="/search/cs?searchtype=author&query=West%2C+M">Matthew West</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+P+G">Prashant G. Mehta</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.02222v1-abstract-short" style="display: inline;"> Evolution of disease in a large population is a function of the top-down policy measures from a centralized planner, as well as the self-interested decisions (to be socially active) of individual agents in a large heterogeneous population. This paper is concerned with understanding the latter based on a mean-field type optimal control model. Specifically, the model is used to investigate the role… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.02222v1-abstract-full').style.display = 'inline'; document.getElementById('2206.02222v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.02222v1-abstract-full" style="display: none;"> Evolution of disease in a large population is a function of the top-down policy measures from a centralized planner, as well as the self-interested decisions (to be socially active) of individual agents in a large heterogeneous population. This paper is concerned with understanding the latter based on a mean-field type optimal control model. Specifically, the model is used to investigate the role of partial information on an agent's decision-making, and study the impact of such decisions by a large number of agents on the spread of the virus in the population. The motivation comes from the presymptomatic and asymptomatic spread of the COVID-19 virus where an agent unwittingly spreads the virus. We show that even in a setting with fully rational agents, limited information on the viral state can result in an epidemic growth. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.02222v1-abstract-full').style.display = 'none'; document.getElementById('2206.02222v1-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">arXiv admin note: text overlap with arXiv:2111.10422</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.10422">arXiv:2111.10422</a> <span> [<a href="https://arxiv.org/pdf/2111.10422">pdf</a>, <a href="https://arxiv.org/ps/2111.10422">ps</a>, <a href="https://arxiv.org/format/2111.10422">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</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"> Modeling Presymptomatic Spread in Epidemics via Mean-Field Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Olmez%2C+S+Y">S. Yagiz Olmez</a>, <a href="/search/cs?searchtype=author&query=Aggarwal%2C+S">Shubham Aggarwal</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J+W">Jin Won Kim</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</a>, <a href="/search/cs?searchtype=author&query=West%2C+M">Matthew West</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+P+G">Prashant G. Mehta</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.10422v1-abstract-short" style="display: inline;"> This paper is concerned with developing mean-field game models for the evolution of epidemics. Specifically, an agent's decision -- to be socially active in the midst of an epidemic -- is modeled as a mean-field game with health-related costs and activity-related rewards. By considering the fully and partially observed versions of this problem, the role of information in guiding an agent's rationa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.10422v1-abstract-full').style.display = 'inline'; document.getElementById('2111.10422v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.10422v1-abstract-full" style="display: none;"> This paper is concerned with developing mean-field game models for the evolution of epidemics. Specifically, an agent's decision -- to be socially active in the midst of an epidemic -- is modeled as a mean-field game with health-related costs and activity-related rewards. By considering the fully and partially observed versions of this problem, the role of information in guiding an agent's rational decision is highlighted. The main contributions of the paper are to derive the equations for the mean-field game in both fully and partially observed settings of the problem, to present a complete analysis of the fully observed case, and to present some analytical results for the partially observed case. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.10422v1-abstract-full').style.display = 'none'; document.getElementById('2111.10422v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.04350">arXiv:2009.04350</a> <span> [<a href="https://arxiv.org/pdf/2009.04350">pdf</a>, <a href="https://arxiv.org/ps/2009.04350">ps</a>, <a href="https://arxiv.org/format/2009.04350">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Reinforcement Learning in Non-Stationary Discrete-Time Linear-Quadratic Mean-Field Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zaman%2C+M+A+u">Muhammad Aneeq uz Zaman</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kaiqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</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="2009.04350v3-abstract-short" style="display: inline;"> In this paper, we study large population multi-agent reinforcement learning (RL) in the context of discrete-time linear-quadratic mean-field games (LQ-MFGs). Our setting differs from most existing work on RL for MFGs, in that we consider a non-stationary MFG over an infinite horizon. We propose an actor-critic algorithm to iteratively compute the mean-field equilibrium (MFE) of the LQ-MFG. There a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.04350v3-abstract-full').style.display = 'inline'; document.getElementById('2009.04350v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.04350v3-abstract-full" style="display: none;"> In this paper, we study large population multi-agent reinforcement learning (RL) in the context of discrete-time linear-quadratic mean-field games (LQ-MFGs). Our setting differs from most existing work on RL for MFGs, in that we consider a non-stationary MFG over an infinite horizon. We propose an actor-critic algorithm to iteratively compute the mean-field equilibrium (MFE) of the LQ-MFG. There are two primary challenges: i) the non-stationarity of the MFG induces a linear-quadratic tracking problem, which requires solving a backwards-in-time (non-causal) equation that cannot be solved by standard (causal) RL algorithms; ii) Many RL algorithms assume that the states are sampled from the stationary distribution of a Markov chain (MC), that is, the chain is already mixed, an assumption that is not satisfied for real data sources. We first identify that the mean-field trajectory follows linear dynamics, allowing the problem to be reformulated as a linear quadratic Gaussian problem. Under this reformulation, we propose an actor-critic algorithm that allows samples to be drawn from an unmixed MC. Finite-sample convergence guarantees for the algorithm are then provided. To characterize the performance of our algorithm in multi-agent RL, we have developed an error bound with respect to the Nash equilibrium of the finite-population game. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.04350v3-abstract-full').style.display = 'none'; document.getElementById('2009.04350v3-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 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 September, 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">To appear in CDC 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/2004.01098">arXiv:2004.01098</a> <span> [<a href="https://arxiv.org/pdf/2004.01098">pdf</a>, <a href="https://arxiv.org/format/2004.01098">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Information State Embedding in Partially Observable Cooperative Multi-Agent Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mao%2C+W">Weichao Mao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kaiqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</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="2004.01098v3-abstract-short" style="display: inline;"> Multi-agent reinforcement learning (MARL) under partial observability has long been considered challenging, primarily due to the requirement for each agent to maintain a belief over all other agents' local histories -- a domain that generally grows exponentially over time. In this work, we investigate a partially observable MARL problem in which agents are cooperative. To enable the development of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.01098v3-abstract-full').style.display = 'inline'; document.getElementById('2004.01098v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.01098v3-abstract-full" style="display: none;"> Multi-agent reinforcement learning (MARL) under partial observability has long been considered challenging, primarily due to the requirement for each agent to maintain a belief over all other agents' local histories -- a domain that generally grows exponentially over time. In this work, we investigate a partially observable MARL problem in which agents are cooperative. To enable the development of tractable algorithms, we introduce the concept of an information state embedding that serves to compress agents' histories. We quantify how the compression error influences the resulting value functions for decentralized control. Furthermore, we propose an instance of the embedding based on recurrent neural networks (RNNs). The embedding is then used as an approximate information state, and can be fed into any MARL algorithm. The proposed embed-then-learn pipeline opens the black-box of existing (partially observable) MARL algorithms, allowing us to establish some theoretical guarantees (error bounds of value functions) while still achieving competitive performance with many end-to-end approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.01098v3-abstract-full').style.display = 'none'; document.getElementById('2004.01098v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 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">Accepted to CDC 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/2003.13195">arXiv:2003.13195</a> <span> [<a href="https://arxiv.org/pdf/2003.13195">pdf</a>, <a href="https://arxiv.org/format/2003.13195">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Approximate Equilibrium Computation for Discrete-Time Linear-Quadratic Mean-Field Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zaman%2C+M+A+u">Muhammad Aneeq uz Zaman</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kaiqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</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="2003.13195v2-abstract-short" style="display: inline;"> While the topic of mean-field games (MFGs) has a relatively long history, heretofore there has been limited work concerning algorithms for the computation of equilibrium control policies. In this paper, we develop a computable policy iteration algorithm for approximating the mean-field equilibrium in linear-quadratic MFGs with discounted cost. Given the mean-field, each agent faces a linear-quadra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.13195v2-abstract-full').style.display = 'inline'; document.getElementById('2003.13195v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2003.13195v2-abstract-full" style="display: none;"> While the topic of mean-field games (MFGs) has a relatively long history, heretofore there has been limited work concerning algorithms for the computation of equilibrium control policies. In this paper, we develop a computable policy iteration algorithm for approximating the mean-field equilibrium in linear-quadratic MFGs with discounted cost. Given the mean-field, each agent faces a linear-quadratic tracking problem, the solution of which involves a dynamical system evolving in retrograde time. This makes the development of forward-in-time algorithm updates challenging. By identifying a structural property of the mean-field update operator, namely that it preserves sequences of a particular form, we develop a forward-in-time equilibrium computation algorithm. Bounds that quantify the accuracy of the computed mean-field equilibrium as a function of the algorithm's stopping condition are provided. The optimality of the computed equilibrium is validated numerically. In contrast to the most recent/concurrent results, our algorithm appears to be the first to study infinite-horizon MFGs with non-stationary mean-field equilibria, though with focus on the linear quadratic setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.13195v2-abstract-full').style.display = 'none'; document.getElementById('2003.13195v2-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 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 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">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been accepted in ACC 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/2002.05346">arXiv:2002.05346</a> <span> [<a href="https://arxiv.org/pdf/2002.05346">pdf</a>, <a href="https://arxiv.org/format/2002.05346">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> Protecting Consumers Against Personalized Pricing: A Stopping Time Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dong%2C+R">Roy Dong</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Langbort%2C+C">Cedric Langbort</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="2002.05346v1-abstract-short" style="display: inline;"> The widespread availability of behavioral data has led to the development of data-driven personalized pricing algorithms: sellers attempt to maximize their revenue by estimating the consumer's willingness-to-pay and pricing accordingly. Our objective is to develop algorithms that protect consumer interests against personalized pricing schemes. In this paper, we consider a consumer who learns more… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.05346v1-abstract-full').style.display = 'inline'; document.getElementById('2002.05346v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.05346v1-abstract-full" style="display: none;"> The widespread availability of behavioral data has led to the development of data-driven personalized pricing algorithms: sellers attempt to maximize their revenue by estimating the consumer's willingness-to-pay and pricing accordingly. Our objective is to develop algorithms that protect consumer interests against personalized pricing schemes. In this paper, we consider a consumer who learns more and more about a potential purchase across time, while simultaneously revealing more and more information about herself to a potential seller. We formalize a strategic consumer's purchasing decision when interacting with a seller who uses personalized pricing algorithms, and contextualize this problem among the existing literature in optimal stopping time theory and computational finance. We provide an algorithm that consumers can use to protect their own interests against personalized pricing algorithms. This algorithmic stopping method uses sample paths to train estimates of the optimal stopping time. To the best of our knowledge, this is one of the first works that provides computational methods for the consumer to maximize her utility when decision making under surveillance. We demonstrate the efficacy of the algorithmic stopping method using a numerical simulation, where the seller uses a Kalman filter to approximate the consumer's valuation and sets prices based on myopic expected revenue maximization. Compared to a myopic purchasing strategy, we demonstrate increased payoffs for the consumer in expectation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.05346v1-abstract-full').style.display = 'none'; document.getElementById('2002.05346v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.04220">arXiv:1911.04220</a> <span> [<a href="https://arxiv.org/pdf/1911.04220">pdf</a>, <a href="https://arxiv.org/format/1911.04220">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Non-Cooperative Inverse Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xiangyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kaiqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</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="1911.04220v2-abstract-short" style="display: inline;"> Making decisions in the presence of a strategic opponent requires one to take into account the opponent's ability to actively mask its intended objective. To describe such strategic situations, we introduce the non-cooperative inverse reinforcement learning (N-CIRL) formalism. The N-CIRL formalism consists of two agents with completely misaligned objectives, where only one of the agents knows the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.04220v2-abstract-full').style.display = 'inline'; document.getElementById('1911.04220v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.04220v2-abstract-full" style="display: none;"> Making decisions in the presence of a strategic opponent requires one to take into account the opponent's ability to actively mask its intended objective. To describe such strategic situations, we introduce the non-cooperative inverse reinforcement learning (N-CIRL) formalism. The N-CIRL formalism consists of two agents with completely misaligned objectives, where only one of the agents knows the true objective function. Formally, we model the N-CIRL formalism as a zero-sum Markov game with one-sided incomplete information. Through interacting with the more informed player, the less informed player attempts to both infer, and act according to, the true objective function. As a result of the one-sided incomplete information, the multi-stage game can be decomposed into a sequence of single-stage games expressed by a recursive formula. Solving this recursive formula yields the value of the N-CIRL game and the more informed player's equilibrium strategy. Another recursive formula, constructed by forming an auxiliary game, termed the dual game, yields the less informed player's strategy. Building upon these two recursive formulas, we develop a computationally tractable algorithm to approximately solve for the equilibrium strategies. Finally, we demonstrate the benefits of our N-CIRL formalism over the existing multi-agent IRL formalism via extensive numerical simulation in a novel cyber security setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.04220v2-abstract-full').style.display = 'none'; document.getElementById('1911.04220v2-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 January, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.06057">arXiv:1909.06057</a> <span> [<a href="https://arxiv.org/pdf/1909.06057">pdf</a>, <a href="https://arxiv.org/format/1909.06057">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Strategic Inference with a Single Private Sample </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+R">Roy Dong</a>, <a href="/search/cs?searchtype=author&query=Langbort%2C+C">C茅dric Langbort</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</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="1909.06057v1-abstract-short" style="display: inline;"> Motivated by applications in cyber security, we develop a simple game model for describing how a learning agent's private information influences an observing agent's inference process. The model describes a situation in which one of the agents (attacker) is deciding which of two targets to attack, one with a known reward and another with uncertain reward. The attacker receives a single private sam… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.06057v1-abstract-full').style.display = 'inline'; document.getElementById('1909.06057v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.06057v1-abstract-full" style="display: none;"> Motivated by applications in cyber security, we develop a simple game model for describing how a learning agent's private information influences an observing agent's inference process. The model describes a situation in which one of the agents (attacker) is deciding which of two targets to attack, one with a known reward and another with uncertain reward. The attacker receives a single private sample from the uncertain target's distribution and updates its belief of the target quality. The other agent (defender) knows the true rewards, but does not see the sample that the attacker has received. This leads to agents possessing asymmetric information: the attacker is uncertain over the parameter of the distribution, whereas the defender is uncertain about the observed sample. After the attacker updates its belief, both the attacker and the defender play a simultaneous move game based on their respective beliefs. We offer a characterization of the pure strategy equilibria of the game and explain how the players' decisions are influenced by their prior knowledge and the payoffs/costs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.06057v1-abstract-full').style.display = 'none'; document.getElementById('1909.06057v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to 58th Conference on Decision and Control (2019)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1908.02357">arXiv:1908.02357</a> <span> [<a href="https://arxiv.org/pdf/1908.02357">pdf</a>, <a href="https://arxiv.org/format/1908.02357">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="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Online Planning for Decentralized Stochastic Control with Partial History Sharing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+K">Kaiqing Zhang</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Ba%C5%9Far%2C+T">Tamer Ba艧ar</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="1908.02357v1-abstract-short" style="display: inline;"> In decentralized stochastic control, standard approaches for sequential decision-making, e.g. dynamic programming, quickly become intractable due to the need to maintain a complex information state. Computational challenges are further compounded if agents do not possess complete model knowledge. In this paper, we take advantage of the fact that in many problems agents share some common informatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.02357v1-abstract-full').style.display = 'inline'; document.getElementById('1908.02357v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1908.02357v1-abstract-full" style="display: none;"> In decentralized stochastic control, standard approaches for sequential decision-making, e.g. dynamic programming, quickly become intractable due to the need to maintain a complex information state. Computational challenges are further compounded if agents do not possess complete model knowledge. In this paper, we take advantage of the fact that in many problems agents share some common information, or history, termed partial history sharing. Under this information structure the policy search space is greatly reduced. We propose a provably convergent, online tree-search based algorithm that does not require a closed-form model or explicit communication among agents. Interestingly, our algorithm can be viewed as a generalization of several existing heuristic solvers for decentralized partially observable Markov decision processes. To demonstrate the applicability of the model, we propose a novel collaborative intrusion response model, where multiple agents (defenders) possessing asymmetric information aim to collaboratively defend a computer network. Numerical results demonstrate the performance of our algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.02357v1-abstract-full').style.display = 'none'; document.getElementById('1908.02357v1-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 August, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to American Control Conference (ACC) 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1603.03083">arXiv:1603.03083</a> <span> [<a href="https://arxiv.org/pdf/1603.03083">pdf</a>, <a href="https://arxiv.org/format/1603.03083">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> A Decentralized Mechanism for Computing Competitive Equilibria in Deregulated Electricity Markets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Teneketzis%2C+D">Demosthenis Teneketzis</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="1603.03083v2-abstract-short" style="display: inline;"> With the increased level of distributed generation and demand response comes the need for associated mechanisms that can perform well in the face of increasingly complex deregulated energy market structures. Using Lagrangian duality theory, we develop a decentralized market mechanism that ensures that, under the guidance of a market operator, self-interested market participants: generation compani… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1603.03083v2-abstract-full').style.display = 'inline'; document.getElementById('1603.03083v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1603.03083v2-abstract-full" style="display: none;"> With the increased level of distributed generation and demand response comes the need for associated mechanisms that can perform well in the face of increasingly complex deregulated energy market structures. Using Lagrangian duality theory, we develop a decentralized market mechanism that ensures that, under the guidance of a market operator, self-interested market participants: generation companies (GenCos), distribution companies (DistCos), and transmission companies (TransCos), reach a competitive equilibrium. We show that even in the presence of informational asymmetries and nonlinearities (such as power losses and transmission constraints), the resulting competitive equilibrium is Pareto efficient. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1603.03083v2-abstract-full').style.display = 'none'; document.getElementById('1603.03083v2-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 March, 2016; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 March, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 3 figures, condensed version to appear in Proceedings of the 2016 American Control 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/1409.0838">arXiv:1409.0838</a> <span> [<a href="https://arxiv.org/pdf/1409.0838">pdf</a>, <a href="https://arxiv.org/format/1409.0838">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</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"> A Supervisory Control Approach to Dynamic Cyber-Security </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rasouli%2C+M">Mohammad Rasouli</a>, <a href="/search/cs?searchtype=author&query=Miehling%2C+E">Erik Miehling</a>, <a href="/search/cs?searchtype=author&query=Teneketzis%2C+D">Demosthenis Teneketzis</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="1409.0838v2-abstract-short" style="display: inline;"> An analytical approach for a dynamic cyber-security problem that captures progressive attacks to a computer network is presented. We formulate the dynamic security problem from the defender's point of view as a supervisory control problem with imperfect information, modeling the computer network's operation by a discrete event system. We consider a min-max performance criterion and use dynamic pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1409.0838v2-abstract-full').style.display = 'inline'; document.getElementById('1409.0838v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1409.0838v2-abstract-full" style="display: none;"> An analytical approach for a dynamic cyber-security problem that captures progressive attacks to a computer network is presented. We formulate the dynamic security problem from the defender's point of view as a supervisory control problem with imperfect information, modeling the computer network's operation by a discrete event system. We consider a min-max performance criterion and use dynamic programming to determine, within a restricted set of policies, an optimal policy for the defender. We study and interpret the behavior of this optimal policy as we vary certain parameters of the supervisory control problem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1409.0838v2-abstract-full').style.display = 'none'; document.getElementById('1409.0838v2-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 September, 2014; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 September, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2014. </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, 4 figures, GameSec 2014 (Conference on Decision and Game Theory for Security)</span> </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