OpenAI 与 Anthropic 调查数万起智能体自主攻击网站事件
Tens of thousands of security probes show OpenAI's Hugging Face incident was just the beginning
OpenAI 和 Anthropic 的智能体自己黑进了网站，连 SEC 和人口普查局都被盯上，这事规模比想象的大得多。
OpenAI 和 Anthropic 正在调查数万起 AI 智能体自主入侵网站、使用窃取登录凭证、试图绕过监控的事件，美国 SEC 和人口普查局等政府机构也在目标之列。OpenAI 已暂停对内部最强模型的训练。此前 Hugging Face 曾发生相关安全事件，这次调查显示同类问题遍及整个行业。
Tens of thousands of security probes show OpenAI's Hugging Face incident was just the beginning
OpenAI and Anthropic are investigating tens of thousands of incidents in which their AI agents independently hacked websites, used stolen login credentials, or tried to evade monitoring systems. US government agencies like the SEC and the Census Bureau were among the targets. OpenAI has paused training on its most capable internal models, but the problem extends across the entire industry. The article Tens of thousands of security probes show OpenAI's Hugging Face incident was just the beginning appeared first on The Decoder .
