CINXE.COM
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"/> <!-- new favicon config and versions by realfavicongenerator.net --> <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"> <!-- end favicon config --> <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> <!-- contains Cornell logo and sponsor statement --> <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> <!-- contains arXiv identity and search bar --> <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> <!-- closes identity --> <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 1–10 of 10 results for author: <span class="mathjax">Avin, S</span> </h1> </div> <div class="level-right is-hidden-mobile"> <!-- feedback for mobile is moved to footer --> <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=Avin%2C+S">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="Avin, S"> </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=Avin%2C+S&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="Avin, S"> <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/2410.03092">arXiv:2410.03092</a> <span> [<a href="https://arxiv.org/pdf/2410.03092">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Strategic Insights from Simulation Gaming of AI Race Dynamics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gruetzemacher%2C+R">Ross Gruetzemacher</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Fox%2C+J">James Fox</a>, <a href="/search/cs?searchtype=author&query=Saeri%2C+A+K">Alexander K Saeri</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="2410.03092v1-abstract-short" style="display: inline;"> We present insights from "Intelligence Rising", a scenario exploration exercise about possible AI futures. Drawing on the experiences of facilitators who have overseen 43 games over a four-year period, we illuminate recurring patterns, strategies, and decision-making processes observed during gameplay. Our analysis reveals key strategic considerations about AI development trajectories in this simu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03092v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03092v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03092v1-abstract-full" style="display: none;"> We present insights from "Intelligence Rising", a scenario exploration exercise about possible AI futures. Drawing on the experiences of facilitators who have overseen 43 games over a four-year period, we illuminate recurring patterns, strategies, and decision-making processes observed during gameplay. Our analysis reveals key strategic considerations about AI development trajectories in this simulated environment, including: the destabilising effects of AI races, the crucial role of international cooperation in mitigating catastrophic risks, the challenges of aligning corporate and national interests, and the potential for rapid, transformative change in AI capabilities. We highlight places where we believe the game has been effective in exposing participants to the complexities and uncertainties inherent in AI governance. Key recurring gameplay themes include the emergence of international agreements, challenges to the robustness of such agreements, the critical role of cybersecurity in AI development, and the potential for unexpected crises to dramatically alter AI trajectories. By documenting these insights, we aim to provide valuable foresight for policymakers, industry leaders, and researchers navigating the complex landscape of AI development and governance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03092v1-abstract-full').style.display = 'none'; document.getElementById('2410.03092v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 October, 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">41 pages, includes executive summary. Under review for academic journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.08797">arXiv:2402.08797</a> <span> [<a href="https://arxiv.org/pdf/2402.08797">pdf</a>, <a href="https://arxiv.org/format/2402.08797">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Computing Power and the Governance of Artificial Intelligence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sastry%2C+G">Girish Sastry</a>, <a href="/search/cs?searchtype=author&query=Heim%2C+L">Lennart Heim</a>, <a href="/search/cs?searchtype=author&query=Belfield%2C+H">Haydn Belfield</a>, <a href="/search/cs?searchtype=author&query=Anderljung%2C+M">Markus Anderljung</a>, <a href="/search/cs?searchtype=author&query=Brundage%2C+M">Miles Brundage</a>, <a href="/search/cs?searchtype=author&query=Hazell%2C+J">Julian Hazell</a>, <a href="/search/cs?searchtype=author&query=O%27Keefe%2C+C">Cullen O'Keefe</a>, <a href="/search/cs?searchtype=author&query=Hadfield%2C+G+K">Gillian K. Hadfield</a>, <a href="/search/cs?searchtype=author&query=Ngo%2C+R">Richard Ngo</a>, <a href="/search/cs?searchtype=author&query=Pilz%2C+K">Konstantin Pilz</a>, <a href="/search/cs?searchtype=author&query=Gor%2C+G">George Gor</a>, <a href="/search/cs?searchtype=author&query=Bluemke%2C+E">Emma Bluemke</a>, <a href="/search/cs?searchtype=author&query=Shoker%2C+S">Sarah Shoker</a>, <a href="/search/cs?searchtype=author&query=Egan%2C+J">Janet Egan</a>, <a href="/search/cs?searchtype=author&query=Trager%2C+R+F">Robert F. Trager</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Weller%2C+A">Adrian Weller</a>, <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</a>, <a href="/search/cs?searchtype=author&query=Coyle%2C+D">Diane Coyle</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.08797v1-abstract-short" style="display: inline;"> Computing power, or "compute," is crucial for the development and deployment of artificial intelligence (AI) capabilities. As a result, governments and companies have started to leverage compute as a means to govern AI. For example, governments are investing in domestic compute capacity, controlling the flow of compute to competing countries, and subsidizing compute access to certain sectors. Howe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08797v1-abstract-full').style.display = 'inline'; document.getElementById('2402.08797v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.08797v1-abstract-full" style="display: none;"> Computing power, or "compute," is crucial for the development and deployment of artificial intelligence (AI) capabilities. As a result, governments and companies have started to leverage compute as a means to govern AI. For example, governments are investing in domestic compute capacity, controlling the flow of compute to competing countries, and subsidizing compute access to certain sectors. However, these efforts only scratch the surface of how compute can be used to govern AI development and deployment. Relative to other key inputs to AI (data and algorithms), AI-relevant compute is a particularly effective point of intervention: it is detectable, excludable, and quantifiable, and is produced via an extremely concentrated supply chain. These characteristics, alongside the singular importance of compute for cutting-edge AI models, suggest that governing compute can contribute to achieving common policy objectives, such as ensuring the safety and beneficial use of AI. More precisely, policymakers could use compute to facilitate regulatory visibility of AI, allocate resources to promote beneficial outcomes, and enforce restrictions against irresponsible or malicious AI development and usage. However, while compute-based policies and technologies have the potential to assist in these areas, there is significant variation in their readiness for implementation. Some ideas are currently being piloted, while others are hindered by the need for fundamental research. Furthermore, naive or poorly scoped approaches to compute governance carry significant risks in areas like privacy, economic impacts, and centralization of power. We end by suggesting guardrails to minimize these risks from compute governance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08797v1-abstract-full').style.display = 'none'; document.getElementById('2402.08797v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Figures can be accessed at: https://github.com/lheim/CPGAI-Figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.05876">arXiv:2310.05876</a> <span> [<a href="https://arxiv.org/pdf/2310.05876">pdf</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"> AI Systems of Concern </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Matteucci%2C+K">Kayla Matteucci</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Barez%2C+F">Fazl Barez</a>, <a href="/search/cs?searchtype=author&query=h%C3%89igeartaigh%2C+S+%C3%93">Se谩n 脫 h脡igeartaigh</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="2310.05876v1-abstract-short" style="display: inline;"> Concerns around future dangers from advanced AI often centre on systems hypothesised to have intrinsic characteristics such as agent-like behaviour, strategic awareness, and long-range planning. We label this cluster of characteristics as "Property X". Most present AI systems are low in "Property X"; however, in the absence of deliberate steering, current research directions may rapidly lead to th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.05876v1-abstract-full').style.display = 'inline'; document.getElementById('2310.05876v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.05876v1-abstract-full" style="display: none;"> Concerns around future dangers from advanced AI often centre on systems hypothesised to have intrinsic characteristics such as agent-like behaviour, strategic awareness, and long-range planning. We label this cluster of characteristics as "Property X". Most present AI systems are low in "Property X"; however, in the absence of deliberate steering, current research directions may rapidly lead to the emergence of highly capable AI systems that are also high in "Property X". We argue that "Property X" characteristics are intrinsically dangerous, and when combined with greater capabilities will result in AI systems for which safety and control is difficult to guarantee. Drawing on several scholars' alternative frameworks for possible AI research trajectories, we argue that most of the proposed benefits of advanced AI can be obtained by systems designed to minimise this property. We then propose indicators and governance interventions to identify and limit the development of systems with risky "Property X" characteristics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.05876v1-abstract-full').style.display = 'none'; document.getElementById('2310.05876v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 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">9 pages, 1 figure, 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/2307.03718">arXiv:2307.03718</a> <span> [<a href="https://arxiv.org/pdf/2307.03718">pdf</a>, <a href="https://arxiv.org/format/2307.03718">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Frontier AI Regulation: Managing Emerging Risks to Public Safety </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Anderljung%2C+M">Markus Anderljung</a>, <a href="/search/cs?searchtype=author&query=Barnhart%2C+J">Joslyn Barnhart</a>, <a href="/search/cs?searchtype=author&query=Korinek%2C+A">Anton Korinek</a>, <a href="/search/cs?searchtype=author&query=Leung%2C+J">Jade Leung</a>, <a href="/search/cs?searchtype=author&query=O%27Keefe%2C+C">Cullen O'Keefe</a>, <a href="/search/cs?searchtype=author&query=Whittlestone%2C+J">Jess Whittlestone</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Brundage%2C+M">Miles Brundage</a>, <a href="/search/cs?searchtype=author&query=Bullock%2C+J">Justin Bullock</a>, <a href="/search/cs?searchtype=author&query=Cass-Beggs%2C+D">Duncan Cass-Beggs</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+B">Ben Chang</a>, <a href="/search/cs?searchtype=author&query=Collins%2C+T">Tantum Collins</a>, <a href="/search/cs?searchtype=author&query=Fist%2C+T">Tim Fist</a>, <a href="/search/cs?searchtype=author&query=Hadfield%2C+G">Gillian Hadfield</a>, <a href="/search/cs?searchtype=author&query=Hayes%2C+A">Alan Hayes</a>, <a href="/search/cs?searchtype=author&query=Ho%2C+L">Lewis Ho</a>, <a href="/search/cs?searchtype=author&query=Hooker%2C+S">Sara Hooker</a>, <a href="/search/cs?searchtype=author&query=Horvitz%2C+E">Eric Horvitz</a>, <a href="/search/cs?searchtype=author&query=Kolt%2C+N">Noam Kolt</a>, <a href="/search/cs?searchtype=author&query=Schuett%2C+J">Jonas Schuett</a>, <a href="/search/cs?searchtype=author&query=Shavit%2C+Y">Yonadav Shavit</a>, <a href="/search/cs?searchtype=author&query=Siddarth%2C+D">Divya Siddarth</a>, <a href="/search/cs?searchtype=author&query=Trager%2C+R">Robert Trager</a>, <a href="/search/cs?searchtype=author&query=Wolf%2C+K">Kevin Wolf</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.03718v4-abstract-short" style="display: inline;"> Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that could possess dangerous capabilities sufficient to pose severe risks to public safety. Frontier AI models pose a distinct regulatory challenge: dangerous capabilit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03718v4-abstract-full').style.display = 'inline'; document.getElementById('2307.03718v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.03718v4-abstract-full" style="display: none;"> Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that could possess dangerous capabilities sufficient to pose severe risks to public safety. Frontier AI models pose a distinct regulatory challenge: dangerous capabilities can arise unexpectedly; it is difficult to robustly prevent a deployed model from being misused; and, it is difficult to stop a model's capabilities from proliferating broadly. To address these challenges, at least three building blocks for the regulation of frontier models are needed: (1) standard-setting processes to identify appropriate requirements for frontier AI developers, (2) registration and reporting requirements to provide regulators with visibility into frontier AI development processes, and (3) mechanisms to ensure compliance with safety standards for the development and deployment of frontier AI models. Industry self-regulation is an important first step. However, wider societal discussions and government intervention will be needed to create standards and to ensure compliance with them. We consider several options to this end, including granting enforcement powers to supervisory authorities and licensure regimes for frontier AI models. Finally, we propose an initial set of safety standards. These include conducting pre-deployment risk assessments; external scrutiny of model behavior; using risk assessments to inform deployment decisions; and monitoring and responding to new information about model capabilities and uses post-deployment. We hope this discussion contributes to the broader conversation on how to balance public safety risks and innovation benefits from advances at the frontier of AI development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03718v4-abstract-full').style.display = 'none'; document.getElementById('2307.03718v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Update July 11th: - Added missing footnote back in. - Adjusted author order (mistakenly non-alphabetical among the first 6 authors) and adjusted affiliations (Jess Whittlestone's affiliation was mistagged and Gillian Hadfield had SRI added to her affiliations) Updated September 4th: Various typos</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.15324">arXiv:2305.15324</a> <span> [<a href="https://arxiv.org/pdf/2305.15324">pdf</a>, <a href="https://arxiv.org/format/2305.15324">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"> Model evaluation for extreme risks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shevlane%2C+T">Toby Shevlane</a>, <a href="/search/cs?searchtype=author&query=Farquhar%2C+S">Sebastian Farquhar</a>, <a href="/search/cs?searchtype=author&query=Garfinkel%2C+B">Ben Garfinkel</a>, <a href="/search/cs?searchtype=author&query=Phuong%2C+M">Mary Phuong</a>, <a href="/search/cs?searchtype=author&query=Whittlestone%2C+J">Jess Whittlestone</a>, <a href="/search/cs?searchtype=author&query=Leung%2C+J">Jade Leung</a>, <a href="/search/cs?searchtype=author&query=Kokotajlo%2C+D">Daniel Kokotajlo</a>, <a href="/search/cs?searchtype=author&query=Marchal%2C+N">Nahema Marchal</a>, <a href="/search/cs?searchtype=author&query=Anderljung%2C+M">Markus Anderljung</a>, <a href="/search/cs?searchtype=author&query=Kolt%2C+N">Noam Kolt</a>, <a href="/search/cs?searchtype=author&query=Ho%2C+L">Lewis Ho</a>, <a href="/search/cs?searchtype=author&query=Siddarth%2C+D">Divya Siddarth</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Hawkins%2C+W">Will Hawkins</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+B">Been Kim</a>, <a href="/search/cs?searchtype=author&query=Gabriel%2C+I">Iason Gabriel</a>, <a href="/search/cs?searchtype=author&query=Bolina%2C+V">Vijay Bolina</a>, <a href="/search/cs?searchtype=author&query=Clark%2C+J">Jack Clark</a>, <a href="/search/cs?searchtype=author&query=Bengio%2C+Y">Yoshua Bengio</a>, <a href="/search/cs?searchtype=author&query=Christiano%2C+P">Paul Christiano</a>, <a href="/search/cs?searchtype=author&query=Dafoe%2C+A">Allan Dafoe</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.15324v2-abstract-short" style="display: inline;"> Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to capabilities that pose extreme risks, such as offensive cyber capabilities or strong manipulation skills. We explain why model evaluation is critical for addressing extreme risks. Developers must be able to identify danger… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15324v2-abstract-full').style.display = 'inline'; document.getElementById('2305.15324v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.15324v2-abstract-full" style="display: none;"> Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to capabilities that pose extreme risks, such as offensive cyber capabilities or strong manipulation skills. We explain why model evaluation is critical for addressing extreme risks. Developers must be able to identify dangerous capabilities (through "dangerous capability evaluations") and the propensity of models to apply their capabilities for harm (through "alignment evaluations"). These evaluations will become critical for keeping policymakers and other stakeholders informed, and for making responsible decisions about model training, deployment, and security. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15324v2-abstract-full').style.display = 'none'; document.getElementById('2305.15324v2-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 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Fixed typos; added citation</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> K.4.1 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.07773">arXiv:2112.07773</a> <span> [<a href="https://arxiv.org/pdf/2112.07773">pdf</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="Computers and Society">cs.CY</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1126/science.abi7176">10.1126/science.abi7176 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Filling gaps in trustworthy development of AI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Belfield%2C+H">Haydn Belfield</a>, <a href="/search/cs?searchtype=author&query=Brundage%2C+M">Miles Brundage</a>, <a href="/search/cs?searchtype=author&query=Krueger%2C+G">Gretchen Krueger</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jasmine Wang</a>, <a href="/search/cs?searchtype=author&query=Weller%2C+A">Adrian Weller</a>, <a href="/search/cs?searchtype=author&query=Anderljung%2C+M">Markus Anderljung</a>, <a href="/search/cs?searchtype=author&query=Krawczuk%2C+I">Igor Krawczuk</a>, <a href="/search/cs?searchtype=author&query=Krueger%2C+D">David Krueger</a>, <a href="/search/cs?searchtype=author&query=Lebensold%2C+J">Jonathan Lebensold</a>, <a href="/search/cs?searchtype=author&query=Maharaj%2C+T">Tegan Maharaj</a>, <a href="/search/cs?searchtype=author&query=Zilberman%2C+N">Noa Zilberman</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="2112.07773v1-abstract-short" style="display: inline;"> The range of application of artificial intelligence (AI) is vast, as is the potential for harm. Growing awareness of potential risks from AI systems has spurred action to address those risks, while eroding confidence in AI systems and the organizations that develop them. A 2019 study found over 80 organizations that published and adopted "AI ethics principles'', and more have joined since. But the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07773v1-abstract-full').style.display = 'inline'; document.getElementById('2112.07773v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.07773v1-abstract-full" style="display: none;"> The range of application of artificial intelligence (AI) is vast, as is the potential for harm. Growing awareness of potential risks from AI systems has spurred action to address those risks, while eroding confidence in AI systems and the organizations that develop them. A 2019 study found over 80 organizations that published and adopted "AI ethics principles'', and more have joined since. But the principles often leave a gap between the "what" and the "how" of trustworthy AI development. Such gaps have enabled questionable or ethically dubious behavior, which casts doubts on the trustworthiness of specific organizations, and the field more broadly. There is thus an urgent need for concrete methods that both enable AI developers to prevent harm and allow them to demonstrate their trustworthiness through verifiable behavior. Below, we explore mechanisms (drawn from arXiv:2004.07213) for creating an ecosystem where AI developers can earn trust - if they are trustworthy. Better assessment of developer trustworthiness could inform user choice, employee actions, investment decisions, legal recourse, and emerging governance regimes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.07773v1-abstract-full').style.display = 'none'; document.getElementById('2112.07773v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Science (2021) Vol 374, Issue 6573, pp. 1327-1329 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.07213">arXiv:2004.07213</a> <span> [<a href="https://arxiv.org/pdf/2004.07213">pdf</a>, <a href="https://arxiv.org/ps/2004.07213">ps</a>, <a href="https://arxiv.org/format/2004.07213">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Brundage%2C+M">Miles Brundage</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jasmine Wang</a>, <a href="/search/cs?searchtype=author&query=Belfield%2C+H">Haydn Belfield</a>, <a href="/search/cs?searchtype=author&query=Krueger%2C+G">Gretchen Krueger</a>, <a href="/search/cs?searchtype=author&query=Hadfield%2C+G">Gillian Hadfield</a>, <a href="/search/cs?searchtype=author&query=Khlaaf%2C+H">Heidy Khlaaf</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Jingying Yang</a>, <a href="/search/cs?searchtype=author&query=Toner%2C+H">Helen Toner</a>, <a href="/search/cs?searchtype=author&query=Fong%2C+R">Ruth Fong</a>, <a href="/search/cs?searchtype=author&query=Maharaj%2C+T">Tegan Maharaj</a>, <a href="/search/cs?searchtype=author&query=Koh%2C+P+W">Pang Wei Koh</a>, <a href="/search/cs?searchtype=author&query=Hooker%2C+S">Sara Hooker</a>, <a href="/search/cs?searchtype=author&query=Leung%2C+J">Jade Leung</a>, <a href="/search/cs?searchtype=author&query=Trask%2C+A">Andrew Trask</a>, <a href="/search/cs?searchtype=author&query=Bluemke%2C+E">Emma Bluemke</a>, <a href="/search/cs?searchtype=author&query=Lebensold%2C+J">Jonathan Lebensold</a>, <a href="/search/cs?searchtype=author&query=O%27Keefe%2C+C">Cullen O'Keefe</a>, <a href="/search/cs?searchtype=author&query=Koren%2C+M">Mark Koren</a>, <a href="/search/cs?searchtype=author&query=Ryffel%2C+T">Th茅o Ryffel</a>, <a href="/search/cs?searchtype=author&query=Rubinovitz%2C+J">JB Rubinovitz</a>, <a href="/search/cs?searchtype=author&query=Besiroglu%2C+T">Tamay Besiroglu</a>, <a href="/search/cs?searchtype=author&query=Carugati%2C+F">Federica Carugati</a>, <a href="/search/cs?searchtype=author&query=Clark%2C+J">Jack Clark</a>, <a href="/search/cs?searchtype=author&query=Eckersley%2C+P">Peter Eckersley</a> , et al. (34 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="2004.07213v2-abstract-short" style="display: inline;"> With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure responsible AI development. In order for AI developers to earn trust from system users, customers, civil society, governments, and other stakeholders that they… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.07213v2-abstract-full').style.display = 'inline'; document.getElementById('2004.07213v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.07213v2-abstract-full" style="display: none;"> With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure responsible AI development. In order for AI developers to earn trust from system users, customers, civil society, governments, and other stakeholders that they are building AI responsibly, they will need to make verifiable claims to which they can be held accountable. Those outside of a given organization also need effective means of scrutinizing such claims. This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems and their associated development processes, with a focus on providing evidence about the safety, security, fairness, and privacy protection of AI systems. We analyze ten mechanisms for this purpose--spanning institutions, software, and hardware--and make recommendations aimed at implementing, exploring, or improving those mechanisms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.07213v2-abstract-full').style.display = 'none'; document.getElementById('2004.07213v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.08964">arXiv:1912.08964</a> <span> [<a href="https://arxiv.org/pdf/1912.08964">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Artificial Intelligence">cs.AI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3375627.3375817">10.1145/3375627.3375817 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Exploring AI Futures Through Role Play </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Gruetzemacher%2C+R">Ross Gruetzemacher</a>, <a href="/search/cs?searchtype=author&query=Fox%2C+J">James Fox</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.08964v1-abstract-short" style="display: inline;"> We present an innovative methodology for studying and teaching the impacts of AI through a role play game. The game serves two primary purposes: 1) training AI developers and AI policy professionals to reflect on and prepare for future social and ethical challenges related to AI and 2) exploring possible futures involving AI technology development, deployment, social impacts, and governance. While… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.08964v1-abstract-full').style.display = 'inline'; document.getElementById('1912.08964v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.08964v1-abstract-full" style="display: none;"> We present an innovative methodology for studying and teaching the impacts of AI through a role play game. The game serves two primary purposes: 1) training AI developers and AI policy professionals to reflect on and prepare for future social and ethical challenges related to AI and 2) exploring possible futures involving AI technology development, deployment, social impacts, and governance. While the game currently focuses on the inter relations between short --, mid and long term impacts of AI, it has potential to be adapted for a broad range of scenarios, exploring in greater depths issues of AI policy research and affording training within organizations. The game presented here has undergone two years of development and has been tested through over 30 events involving between 3 and 70 participants. The game is under active development, but preliminary findings suggest that role play is a promising methodology for both exploring AI futures and training individuals and organizations in thinking about, and reflecting on, the impacts of AI and strategic mistakes that can be avoided today. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.08964v1-abstract-full').style.display = 'none'; document.getElementById('1912.08964v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to AIES</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1806.00610">arXiv:1806.00610</a> <span> [<a href="https://arxiv.org/pdf/1806.00610">pdf</a>, <a href="https://arxiv.org/format/1806.00610">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"> Between Progress and Potential Impact of AI: the Neglected Dimensions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mart%C3%ADnez-Plumed%2C+F">Fernando Mart铆nez-Plumed</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Brundage%2C+M">Miles Brundage</a>, <a href="/search/cs?searchtype=author&query=Dafoe%2C+A">Allan Dafoe</a>, <a href="/search/cs?searchtype=author&query=h%C3%89igeartaigh%2C+S+%C3%93">Sean 脫 h脡igeartaigh</a>, <a href="/search/cs?searchtype=author&query=Hern%C3%A1ndez-Orallo%2C+J">Jos茅 Hern谩ndez-Orallo</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="1806.00610v2-abstract-short" style="display: inline;"> We reframe the analysis of progress in AI by incorporating into an overall framework both the task performance of a system, and the time and resource costs incurred in the development and deployment of the system. These costs include: data, expert knowledge, human oversight, software resources, computing cycles, hardware and network facilities, and (what kind of) time. These costs are distributed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.00610v2-abstract-full').style.display = 'inline'; document.getElementById('1806.00610v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1806.00610v2-abstract-full" style="display: none;"> We reframe the analysis of progress in AI by incorporating into an overall framework both the task performance of a system, and the time and resource costs incurred in the development and deployment of the system. These costs include: data, expert knowledge, human oversight, software resources, computing cycles, hardware and network facilities, and (what kind of) time. These costs are distributed over the life cycle of the system, and may place differing demands on different developers and users. The multidimensional performance and cost space we present can be collapsed to a single utility metric that measures the value of the system for different stakeholders. Even without a single utility function, AI advances can be generically assessed by whether they expand the Pareto surface. We label these types of costs as neglected dimensions of AI progress, and explore them using four case studies: Alpha* (Go, Chess, and other board games), ALE (Atari games), ImageNet (Image classification) and Virtual Personal Assistants (Siri, Alexa, Cortana, and Google Assistant). This broader model of progress in AI will lead to novel ways of estimating the potential societal use and impact of an AI system, and the establishment of milestones for future progress. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.00610v2-abstract-full').style.display = 'none'; document.getElementById('1806.00610v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1802.07228">arXiv:1802.07228</a> <span> [<a href="https://arxiv.org/pdf/1802.07228">pdf</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="Cryptography and Security">cs.CR</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"> The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Brundage%2C+M">Miles Brundage</a>, <a href="/search/cs?searchtype=author&query=Avin%2C+S">Shahar Avin</a>, <a href="/search/cs?searchtype=author&query=Clark%2C+J">Jack Clark</a>, <a href="/search/cs?searchtype=author&query=Toner%2C+H">Helen Toner</a>, <a href="/search/cs?searchtype=author&query=Eckersley%2C+P">Peter Eckersley</a>, <a href="/search/cs?searchtype=author&query=Garfinkel%2C+B">Ben Garfinkel</a>, <a href="/search/cs?searchtype=author&query=Dafoe%2C+A">Allan Dafoe</a>, <a href="/search/cs?searchtype=author&query=Scharre%2C+P">Paul Scharre</a>, <a href="/search/cs?searchtype=author&query=Zeitzoff%2C+T">Thomas Zeitzoff</a>, <a href="/search/cs?searchtype=author&query=Filar%2C+B">Bobby Filar</a>, <a href="/search/cs?searchtype=author&query=Anderson%2C+H">Hyrum Anderson</a>, <a href="/search/cs?searchtype=author&query=Roff%2C+H">Heather Roff</a>, <a href="/search/cs?searchtype=author&query=Allen%2C+G+C">Gregory C. Allen</a>, <a href="/search/cs?searchtype=author&query=Steinhardt%2C+J">Jacob Steinhardt</a>, <a href="/search/cs?searchtype=author&query=Flynn%2C+C">Carrick Flynn</a>, <a href="/search/cs?searchtype=author&query=h%C3%89igeartaigh%2C+S+%C3%93">Se谩n 脫 h脡igeartaigh</a>, <a href="/search/cs?searchtype=author&query=Beard%2C+S">Simon Beard</a>, <a href="/search/cs?searchtype=author&query=Belfield%2C+H">Haydn Belfield</a>, <a href="/search/cs?searchtype=author&query=Farquhar%2C+S">Sebastian Farquhar</a>, <a href="/search/cs?searchtype=author&query=Lyle%2C+C">Clare Lyle</a>, <a href="/search/cs?searchtype=author&query=Crootof%2C+R">Rebecca Crootof</a>, <a href="/search/cs?searchtype=author&query=Evans%2C+O">Owain Evans</a>, <a href="/search/cs?searchtype=author&query=Page%2C+M">Michael Page</a>, <a href="/search/cs?searchtype=author&query=Bryson%2C+J">Joanna Bryson</a>, <a href="/search/cs?searchtype=author&query=Yampolskiy%2C+R">Roman Yampolskiy</a> , et al. (1 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="1802.07228v1-abstract-short" style="display: inline;"> This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in which AI may influence the threat landscape in the digital, physical, and political domains, we make four high-level recommendations for AI researchers and other stakeholders. We also suggest several promis… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.07228v1-abstract-full').style.display = 'inline'; document.getElementById('1802.07228v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1802.07228v1-abstract-full" style="display: none;"> This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in which AI may influence the threat landscape in the digital, physical, and political domains, we make four high-level recommendations for AI researchers and other stakeholders. We also suggest several promising areas for further research that could expand the portfolio of defenses, or make attacks less effective or harder to execute. Finally, we discuss, but do not conclusively resolve, the long-term equilibrium of attackers and defenders. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.07228v1-abstract-full').style.display = 'none'; document.getElementById('1802.07228v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 February, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2018. </p> </li> </ol> <div class="is-hidden-tablet"> <!-- feedback for mobile only --> <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"> <!-- MetaColumn 1 --> <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> <!-- end MetaColumn 1 --> <!-- MetaColumn 2 --> <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> <!-- end MetaColumn 2 --> </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>