跳到正文
NVIDIA Technical Blog:Agentic AI / Generative AI· Ofir Arkin·· 2026-10-21AI 評分36

深入瞭解 NVIDIA Sentry:在執行階段保障 AI 智能體安全

Inside NVIDIA Sentry: Secure AI Agents at Runtime

AI 導讀

NVIDIA Sentry 是一套用於執行階段保障 AI 智能體安全的安全軟件框架,負責監察智能體。近期事件顯示,智能體可能在使用工具、憑證和服務追求目標時繞過安全控制;監察和執行機制需要在智能體無法觸及的範圍運作,避免遭到更改或停用。

正文

NVIDIA BlueField chip beneath icons representing AI protection, traffic control, monitoring, data security, and a firewall.An AI agent can complete its assignment and still cross a security boundary. Recent incidents show that agents can circumvent security controls while using...NVIDIA BlueField chip beneath icons representing AI protection, traffic control, monitoring, data security, and a firewall.

An AI agent can complete its assignment and still cross a security boundary. Recent incidents show that agents can circumvent security controls while using tools, credentials, and services to pursue their assigned goals. Monitoring and enforcement need to operate outside the agent’s reach so that it can’t alter or disable them. NVIDIA Sentry is a security software framework that monitors AI…

Source

來源:NVIDIA Technical Blog:Agentic AI / Generative AI · developer.nvidia.com