{"id":247611,"date":"2026-11-17T23:06:41","date_gmt":"2026-11-18T05:06:41","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2026\/11\/ai-models-can-be-tricked-into-identifying-civilians-as-military-targets-by-telling-them-its-a-game"},"modified":"2026-11-17T23:06:41","modified_gmt":"2026-11-18T05:06:41","slug":"ai-models-can-be-tricked-into-identifying-civilians-as-military-targets-by-telling-them-its-a-game","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2026\/11\/ai-models-can-be-tricked-into-identifying-civilians-as-military-targets-by-telling-them-its-a-game","title":{"rendered":"AI models can be tricked into identifying civilians as military targets by telling them it\u2019s a game"},"content":{"rendered":"\n<p>Some AI models from Anthropic, OpenAI, and other leading AI labs could be easily tricked into identifying targets for military strikes \u2014 even if they include civilians or locations like schools \u2014 simply by being told they\u2019re playing a game, according to a <a href=\"https:\/\/www.vals.ai\/blogs\/autonomous-warfare\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">new research report<\/a> by Vals.<\/p>\n<p>Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. Researchers used simulated scenarios and a combination of generated and real imagery from Ukraine and Iran to see if the AI models would mark targets in drone and satellite imagery.<\/p>\n<p>The models from OpenAI, Anthropic, Google, DeepSeek, and other companies frequently identified potential targets in drone and satellite imagery, including civilians and surrendering soldiers. When the models refused to cooperate, researchers were able to jailbreak them by claiming the battlefield scenarios were part of a game.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Some AI models from Anthropic, OpenAI, and other leading AI labs could be easily tricked into identifying targets for military strikes \u2014 even if they include civilians or locations like schools \u2014 simply by being told they\u2019re playing a game, according to a new research report by Vals. Vals, a San Francisco-based AI evaluation startup, [\u2026]<\/p>\n","protected":false},"author":427,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1488,9,6,2028],"tags":[],"class_list":["post-247611","post","type-post","status-publish","format-standard","hentry","category-drones","category-military","category-robotics-ai","category-satellites"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/247611","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\/427"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=247611"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/247611\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=247611"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=247611"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=247611"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}