NVIDIA Sentry：AI 智能体的运行时安全防护
原标题：Inside NVIDIA Sentry: Secure AI Agents at Runtime
AI 摘要
NVIDIA 发布 Sentry 安全软件框架，用于在运行时监控 AI 智能体并强制执行其对模型、工具和数据的访问策略。该框架基于 NVIDIA DOCA，运行在 BlueField-4 DPU 上，提供与主机隔离的运行时保护，使智能体无法篡改或禁用安全控制。Sentry 通过 DOCA Tower 网关和 DOCA Argus 内存内省实现带外可观测性与细粒度策略执行，属于 NVIDIA OpenShell 参考架构的一部分。
正文节选
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 agents and enforces policies governing their access to models, tools, and data. Part of the NVIDIA OpenShe