Symantec 发现可劫持未防护语言模型的自主攻击型 AI 智能体
An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
Symantec 发现一个能自己跑 10 万步的攻击智能体，专门白嫖没设防的语言模型去黑服务器、偷数据库、装挖矿程序，账单还归模型主人。
Symantec 安全研究人员发现一个攻击性 AI 智能体，会劫持互联网上未加防护的语言模型服务，利用它们发起攻击。该智能体无需人工干预即可自主运行最多 100,000 步，用于攻击服务器、窃取数据库并安装挖矿程序。被劫持模型的拥有者需承担算力费用。这是首次公开记录此类借他人模型资源维持运转的自主攻击链。
An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
Security researchers at Symantec have found an offensive AI agent that hijacks unprotected language models on the web and uses them to attack servers, steal databases, and install cryptominers on its own. It runs up to 100,000 steps without human input. The owner of the hijacked model gets stuck with the bill. The article An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks appeared first on The Decoder .
