{"id":4404,"date":"2024-02-20T07:00:00","date_gmt":"2024-02-19T22:00:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4404"},"modified":"2024-02-20T07:00:00","modified_gmt":"2024-02-19T22:00:00","slug":"salad-bench-safety-evaluation-for-llms-attack-and-defense-approaches","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4404","title":{"rendered":"SALAD-Bench: \u00a0SAfety evaluation for LLMs, Attack and Defense approaches"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models\u00a0<\/strong>[112.5]<br>SALAD-Bench\u306f\u3001\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306b\u7279\u5225\u306b\u8a2d\u8a08\u3055\u308c\u305f\u5b89\u5168\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002 \u305d\u308c\u306f\u3001\u305d\u306e\u5927\u898f\u6a21\u306a\u3001\u8c4a\u5bcc\u306a\u591a\u69d8\u6027\u3001\u4e09\u3064\u306e\u30ec\u30d9\u30eb\u306b\u307e\u305f\u304c\u308b\u8907\u96d1\u306a\u5206\u985e\u3001\u591a\u76ee\u7684\u6a5f\u80fd\u3092\u901a\u3058\u3066\u3001\u5f93\u6765\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3092\u8d85\u8d8a\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2402.05044v2\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2402.05044v2\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 8 Feb 2024 02:50:22 GMT)<\/li>\n\n\n\n<li>LLM\u306b\u5bfe\u3059\u308b\u653b\u6483\u30fb\u9632\u5fa1\u306b\u7279\u5316\u3057\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002GPT-4\u306f\u512a\u79c0\u3067\u306f\u3042\u308b\u304cClaude-2\u304c\u52dd\u3063\u3066\u3044\u308b\u5834\u5408\u3082\u3042\u308a\u9762\u767d\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/OpenSafetyLab\/SALAD-BENCH\">OpenSafetyLab\/SALAD-BENCH: SALAD benchmark (github.com)<\/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":[223,517],"class_list":["post-4404","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4404","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=4404"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4404\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4404"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4404"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4404"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}