{"id":1789,"date":"2025-02-06T05:03:27","date_gmt":"2025-02-06T05:03:27","guid":{"rendered":"https:\/\/serisec.com\/index.php\/2025\/02\/06\/on-generative-ai-security-html\/"},"modified":"2025-02-06T05:03:27","modified_gmt":"2025-02-06T05:03:27","slug":"on-generative-ai-security-html","status":"publish","type":"post","link":"https:\/\/serisec.com\/index.php\/2025\/02\/06\/on-generative-ai-security-html\/","title":{"rendered":"On Generative AI Security"},"content":{"rendered":"\n<div>On Generative AI Security<\/div>\n<p> \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>\n<p>Microsoft\u2019s AI Red Team just published \u201c<a href=\"https:\/\/airedteamwhitepapers.blob.core.windows.net\/lessonswhitepaper\/MS_AIRT_Lessons_eBook.pdf\">Lessons from<br \/>\nRed Teaming 100 Generative AI Products<\/a>.\u201d Their <a href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2025\/01\/13\/3-takeaways-from-red-teaming-100-generative-ai-products\/\">blog post<\/a> lists \u201cthree takeaways,\u201d but the eight lessons in the report itself are more useful:<\/p>\n<blockquote>\n<ol>\n<li>Understand what the system can do and where it is applied.<\/li>\n<li>You don\u2019t have to compute gradients to break an AI system.<\/li>\n<li>AI red teaming is not safety benchmarking.<\/li>\n<li>Automation can help cover more of the risk landscape.<\/li>\n<li>The human element of AI red teaming is crucial.<\/li>\n<li>Responsible AI harms are pervasive but difficult to measure.<\/li>\n<li>LLMs amplify existing security risks and introduce new ones.<\/li>\n<li>The work of securing AI systems will never be complete.<\/li>\n<\/ol>\n<\/blockquote>\n<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Bruce Schneier<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/www.schneier.com\/blog\/archives\/2025\/02\/on-generative-ai-security.html\">Go to bruce schneier<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>On Generative AI Security Microsoft\u2019s AI Red Team just published \u201cLessons from Red Teaming 100 Generative AI Products.\u201d Their blog post lists \u201cthree takeaways,\u201d but the eight lessons in the report itself are more useful: Understand what the system can do and where it is applied. You don\u2019t have to compute gradients to break an [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[167,57,600,267,268,158,1],"tags":[87],"class_list":["post-1789","post","type-post","status-publish","format-standard","hentry","category-ai","category-bruce-schneier","category-computer-security","category-cyberattack","category-llm","category-microsoft","category-uncategorized","tag-bruce-schneier"],"_links":{"self":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts\/1789"}],"collection":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/comments?post=1789"}],"version-history":[{"count":0,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts\/1789\/revisions"}],"wp:attachment":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/media?parent=1789"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/categories?post=1789"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/tags?post=1789"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}