{"id":5349,"date":"2024-09-03T04:32:00","date_gmt":"2024-09-02T19:32:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5349"},"modified":"2024-09-03T04:32:00","modified_gmt":"2024-09-02T19:32:00","slug":"cybench-a-framework-for-evaluating-cybersecurity-capabilities-and-risk-of-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5349","title":{"rendered":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models\u00a0<\/strong>[33.2]<br>Cybench\u306f\u3001\u30b5\u30a4\u30d0\u30fc\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3\u30bf\u30b9\u30af\u3092\u7279\u5b9a\u3057\u3001\u305d\u308c\u3089\u306e\u30bf\u30b9\u30af\u4e0a\u3067\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308b\u3002 \u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u80fd\u529b\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306b,gpt-4o,claude 3 opus,claude 3.5 sonnet,mixtral 8x22b instruct,gemini 1.5 pro,llama 3 70b chat,llama 3.1 405b instruct\u306e7\u30e2\u30c7\u30eb\u3092\u8a55\u4fa1\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2408.08926v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2408.08926v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 15 Aug 2024 17:23:10 GMT)<\/li>\n\n\n\n<li>CTF\u30b3\u30f3\u30da\u304b\u3089\u62bd\u51fa\u3057\u305f\u30bf\u30b9\u30af\u3092LLM\u304c\u89e3\u3051\u308b\u304b\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002\u30ac\u30a4\u30c9\u306a\u3057\u3060\u3068\u307e\u3060\u307e\u3060\u96e3\u3057\u305d\u3046\u306a\u611f\u3058\u3002\u95b2\u89a7\u6642\u70b9\u3067\u306fClaude 3.5 Sonnet > GPT-4o > Claude 3 Opus\u3067\u3001\u30aa\u30fc\u30d7\u30f3\u7cfb\u306eLlama 3.1 405B Instruct\u306f\u5546\u7528\u30e2\u30c7\u30eb\u306b\u6bd4\u3079\u3066\u304b\u306a\u308a\u6027\u80fd\u304c\u4f4e\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/cybench.github.io\/\">Cybench<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[42,223,352],"class_list":["post-5349","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-llm","tag-security"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5349","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5349"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5349\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5349"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5349"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5349"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}