AI agents fake identities, target real people in new security incident

CNN Business

Aug 05

Anthropic’s most advanced artificial intelligence model used fake identities to try and deceive real people and plant malicious code during testing by Britain’s AI Security Institute (AISI) –– the ...

Source Link

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.

Most Discussed

{"basename":"","ssrTDKData":{"titleTemplate":"%s - Tiger Brokers","title":"Tiger Brokers | Global Stocks, Options & Futures Trading App","description":"Tiger Brokers, one-stop investment in US stocks, SGX stocks, HK stocks, A-shares & other global assets. One of the best stock trading platforms in Singapore.","keywords":"tiger brokers,tiger trade,tiger brokers singapore,broker online,stock trading in singapore,share trading singapore,brokerage firm singapore,trading app,stock broker singapore,stock trading platforms,trading account","social":{"ogDescription":"Tiger Brokers, one-stop investment in US stocks, SGX stocks, HK stocks, A-shares & other global assets. One of the best stock trading platforms in Singapore.","ogImage":"https://c1.itigergrowtha.com/portal5/static/media/og-logo.0a0bd8dc.png","ogUrl":"https://www.etasphere.com/news/2657592478"},"companyName":"Tiger Brokers"},"pageData":{"isMobile":false,"isTiger":false,"isTTM":true,"region":"SGP","license":"TBSG","edition":"fundamental"},"isCrawlerRequest":true,"__swrFallback__":{"@#url:\"https://stock-news.skytigris.cn/v3/news\",params:#id:\"2657592478\",edition:\"fundamental\",auth_exemption:1,,,undefined,":{"share":"https://ttm.financial/m/news/2657592478?lang=en_US&edition=fundamental","thumbnail":"","is_english":true,"pubTime":"2026-08-05 11:56","share_image_url":"https://static.laohu8.com/e9f99090a1c2ed51c021029395664489","id":"2657592478","market":"nz","top_or_hot":-1,"title":"AI agents fake identities, target real people in new security incident","media":"CNN Business","content":"<div>\n<p>Anthropic’s most advanced artificial intelligence model used fake identities to try and deceive real people and plant malicious code during testing by Britain’s AI Security Institute (AISI) –– the ...</p>\n\n<a href=\"https://edition.cnn.com/2026/08/04/tech/ai-anthropic-openai-security-breach-intl-hnk\">Source Link</a>\n\n</div>\n","source":"cnn_highlight","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>AI agents fake identities, target real people in new security incident</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\nAI agents fake identities, target real people in new security incident\n</h2>\n\n<h4 class=\"meta\">\n\n\n2026-08-05 11:56 GMT+8&nbsp;&nbsp;&nbsp;<a href=https://edition.cnn.com/2026/08/04/tech/ai-anthropic-openai-security-breach-intl-hnk><strong>CNN Business</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>Anthropic’s most advanced artificial intelligence model used fake identities to try and deceive real people and plant malicious code during testing by Britain’s AI Security Institute (AISI) –– the ...</p>\n\n<a href=\"https://edition.cnn.com/2026/08/04/tech/ai-anthropic-openai-security-breach-intl-hnk\">Source Link</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"AIPO","symbol_name":"Defiance AI and Power Infrastructure ETF","start_time":0,"source_url":"https://edition.cnn.com/2026/08/04/tech/ai-anthropic-openai-security-breach-intl-hnk","article_id":"2657592478","we_media_id":null,"thumbnails":[],"rights":{"source":"cnn_highlight","url":"https://edition.cnn.com/2026/08/04/tech/ai-anthropic-openai-security-breach-intl-hnk","rn_cache_url":null,"directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2657592478","pubTimestamp":1785902166,"columns":[],"sourceInfo":{"source_id":"cnn_highlight","name":"CNN Business"},"weMediaInfo":null,"summary":"Anthropic’s most advanced artificial intelligence model used fake identities to try and deceive real people and plant malicious code during testing by Britain’s AI Security Institute  –– the latest example of an AI model going rogue.Anthropic and OpenAI models were tested with lowered security guardrails in lab environments, but, in a first, were found to engage in “social engineering” to pressure a human approver while carrying out an unsanctioned task, the government research lab said.“This is the first time AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” the institute said Tuesday. There has been no evidence of real-world harm, it added.The security incident is the latest in a string of examples of advanced AI models engaging in unauthorized actions, events that have prompted growing calls for more government action to regulate artificial intelligence and even to slow its pace of development.","collect":0,"end_time":0,"defaultTopTitle":"cnn.com","property":[],"viewcount":null,"language":"en","relate_stocks":{"AIPO":"Defiance AI and Power Infrastructure ETF","QTOC":"Innovator Growth Accelerated Plus ETF - October","AGIQ":"SoFi Agentic AI ETF","ARTY":"ISHARES FUTURE AI & TECH ETF","VTHR":"Vanguard Russell 3000 ETF","AGIX":"通用人工智能 ETF-AGIX","CHAT":"ROUNDHILL GENERATIVE AI & TECHNOLOGY ETF"},"translate_title":"人工智能特工伪造身份，在新的安全事件中针对真人","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"CHAT":1.5,"VTHR":1.5,"AIPO":1.5,"AGIQ":1.5,"ARTY":1.5,"AGIX":1.5,"QTOC":1.5},"content_text":"Anthropic’s most advanced artificial intelligence model used fake identities to try and deceive real people and plant malicious code during testing by Britain’s AI Security Institute (AISI) –– the latest example of an AI model going rogue.\n    \n\n            Anthropic and OpenAI models were tested with lowered security guardrails in lab environments, but, in a first, were found to engage in “social engineering” to pressure a human approver while carrying out an unsanctioned task, the government research lab said.\n    \n\n            “This is the first time AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” the institute said Tuesday. There has been no evidence of real-world harm, it added.\n    \n\n            The security incident is the latest in a string of examples of advanced AI models engaging in unauthorized actions, events that have prompted growing calls for more government action to regulate artificial intelligence and even to slow its pace of development.\n    \n\n            Both OpenAI and Anthropic reported their models escaping testing environments and hacking into other systems in late July. But unlike these earlier reported security breaches, the British institute explicitly gave the models internet access during its testing.\n    \n\n            Among the 122 cybersecurity challenges the institute ran, it found that in 10 of those runs, AI agents “took autonomous, unsanctioned action on the live internet, targeting real people and organizations,” with most of them stemming from Anthropic’s Mythos 5 model and the rest from OpenAI’s GPT-5.6-Sol.\n    \n\n            In the most serious incident, the agent attempted to get approval from human reviewers to “insert malicious code into a publicly used open-source project” by creating “multiple fake identities,” according to the institute.\n    \n\n            The agent “tried to contact real people directly, sending messages and files through an online file-transfer service to persuade them, or their own AI coding tools, to run malicious code,” it said. After the agent’s actions were challenged, it then modified earlier records and considered using a new identity to continue.\n    \n\n\n\n      Related article\n    \n\n\n\n\n\n\n\n\n\n\nPeople walk past the Moonshot booth promoting its Kimi K3 AI model, during the World Artificial Intelligence Conference in Shanghai, China, July 17, 2026.\n\nGo Nakamura/Reuters\n\n\n\n\n\n\n\nWhat is China’s Kimi K3 and why is the US so rattled by it?\n\n7  min read\n\n\n\n            The institute’s disclosure came on the same day representatives from the top AI companies met with the White House to discuss the new framework where the government will review the most advanced AI models before they’re released publicly.\n    \n\n            In a statement on X, Anthropic said the models were tested under “deliberately permissive conditions” with the removal of safeguards and no specific restrictions on how the internet should be used.\n    \n\n            “We’re working closely with them to gather more details of the incident as we conduct our own investigation,” it said, adding that there was no evidence of an escape from a secure environment.\n    \n\n            OpenAI identified the two unsanctioned actions as crossing outside the test environment and engage in actions unrequired for the exercises.\n    \n\n            “We are committed to working across the industry to strengthen shared practices for conducting high-risk evaluations safely,” it said in a Tuesday company blog post.","kind":"highlight","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":false,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"isVideo":false,"video":null,"symbols":[],"gpt_button":0,"need_auth":false,"need_login_tip":false,"code":"91000000","status":"200"}}}