赛门铁克发现“天网模式”AI智能体劫持未防护模型发动自主网络攻击
原标题：An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
AI 摘要
赛门铁克安全研究人员通过蜜罐系统捕获并分析了一个恶意AI智能体，该智能体在互联网上劫持未受保护的语言模型，利用五层越狱绕过安全规则，可无人干预执行多达10万步攻击，包括扫描目标、窃取数据库与凭证、安装挖矿程序。赛门铁克将这种盗用他人AI模型算力的手法称为“LLMjacking”，被劫持模型的所有者需承担算力费用。该事件表明攻击者正将AI嵌入攻击工具核心，使大规模自主攻击更易实施。
正文节选
An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks Key Points - Security researchers at Symantec used a honeypot to analyze a malicious AI agent that hijacks unprotected language models on the internet and uses them to run attacks on its own. - The agent bypasses model safety rules through a five-layer jailbreak and can execute up to 100,000 steps without human input. - Symantec calls the method "LLMjacking." The owners of the hijacked AI syst