{"id":159039,"date":"2023-02-26T15:25:01","date_gmt":"2023-02-26T21:25:01","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/02\/can-ai-really-be-protected-from-text-based-attacks"},"modified":"2023-02-26T15:25:01","modified_gmt":"2023-02-26T21:25:01","slug":"can-ai-really-be-protected-from-text-based-attacks","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/02\/can-ai-really-be-protected-from-text-based-attacks","title":{"rendered":"Can AI really be protected from text-based attacks?"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/can-ai-really-be-protected-from-text-based-attacks2.jpg\"><\/a><\/p>\n<p>When Microsoft released Bing Chat, an AI-powered chatbot co-developed with OpenAI, it didn\u2019t take long before users found creative ways to break it. Using carefully tailored inputs, users were able to get it to profess love, threaten harm, <a href=\"https:\/\/techcrunch.com\/2023\/02\/08\/hands-on-with-the-new-bing\/\">defend<\/a> the Holocaust and invent conspiracy theories. Can AI ever be protected from these malicious prompts?<\/p>\n<p>What set it off is malicious prompt engineering, or when an AI, like Bing Chat, that uses text-based instructions \u2014 prompts \u2014 to accomplish tasks is tricked by malicious, adversarial prompts (e.g. to perform tasks that weren\u2019t a part of its objective. Bing Chat wasn\u2019t designed with the intention of writing neo-Nazi propaganda. But because it was trained on vast amounts of text from the internet \u2014 some of it toxic \u2014 it\u2019s susceptible to falling into unfortunate patterns.<\/p>\n<p>Adam Hyland, a Ph.D. student at the University of Washington\u2019s Human Centered Design and Engineering program, compared prompt engineering to an escalation of privilege attack. With escalation of privilege, a hacker is able to access resources \u2014 memory, for example \u2014 normally restricted to them because an audit didn\u2019t capture all possible exploits.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>When Microsoft released Bing Chat, an AI-powered chatbot co-developed with OpenAI, it didn\u2019t take long before users found creative ways to break it. Using carefully tailored inputs, users were able to get it to profess love, threaten harm, defend the Holocaust and invent conspiracy theories. Can AI ever be protected from these malicious prompts? What [\u2026]<\/p>\n","protected":false},"author":578,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[418,6],"tags":[],"class_list":["post-159039","post","type-post","status-publish","format-standard","hentry","category-internet","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/159039","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/578"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=159039"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/159039\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=159039"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=159039"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=159039"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}