NVIDIA Sentry：在运行时保护 AI 智能体安全
Inside NVIDIA Sentry: Secure AI Agents at Runtime
NVIDIA 推出安全软件框架 Sentry，用于在运行时监控 AI 智能体。该框架的监控与执行机制运行在智能体触及范围之外，使其无法篡改或禁用。此举针对近期出现的智能体在使用工具、凭证和服务时绕过安全控制的事件。
An AI agent can complete its assignment and still cross a security boundary. Recent incidents show that agents can circumvent security controls while using...
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…
来源：NVIDIA Technical Blog · developer.nvidia.com