Microsoft 扩展 Project Perception：持续评估智能体风险并动态控制权限
精选理由
微软把智能体当成内部风险来管：Project Perception 新增持续风险评估、动态权限和威胁遏制，做 Agent 安全的可以看看
Satya Nadella 宣布 Microsoft 将此前提出的"把模型视为内部威胁"原则落地，扩展 Project Perception 项目。新功能包括持续评估智能体（Agent）风险、动态调整权限以及遏制已发生的威胁。安全控制点设置在模型外部，而非依赖模型自身判断。这面向的是企业部署 AI 智能体后的权限与威胁管理场景。
原文 · Satya Nadella
I recently wrote about why we need to treat models as insider risks, with security controls sitting outside the model itself. Today, we're putting that principle into practice by expanding Project Perception with new capabilities to help continuously assess agent risk, adapt permissions, and contain threats. blogs.microsoft.com/blog/2026/10/1… 💬 28 🔄 18 ❤️ 116 👀 15485 📊 39 ⚡
