[论文] Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attesta...
论文概要
研究领域: ML
作者: Viet K. Nguyen, Mohammad I. Husain
发布时间: 2026-11-17
arXiv: 2611.23202
中文摘要
AI 智能体日益跨组织协作,调用工具并与独立实体运营的智能体交互。现有框架支持规划协调,但缺乏验证跨组织身份、执行完整性和授权的共同机制。我们提出 ATI(智能体信任基础设施)——框架无关的安全架构,基于 PKI、零信任架构和远程证明。通过对等组织证书机构(AgentCA)建立联邦信任,无需共享根授权。执行请求前,ATI 验证智能体证书、已批准的模型/工具/系统提示配置,三项策略检查强制执行授权。在模拟 8 组织联邦(6 框架、各 5 智能体团队)中评估,启用全部执法机制后攻击遏制率从 43% 升至 84%,每次请求额外开销约 174 微秒。ATI 已开源。
原文摘要
AI agents increasingly collaborate across organizational boundaries, invoking tools and interacting with agents operated by independent entities. Although existing agent frameworks support planning and coordination, they lack a common mechanism for verifying cross-organizational agent identity, execution integrity, and authorization. We propose the Agent Trust Infrastructure (ATI), a framework-independent security architecture built on Public Key Infrastructure (PKI), Zero Trust Architecture (ZTA), and remote attestation. ATI establishes federated trust through peer organizational certificate authorities (AgentCAs), eliminating the need for a shared root authority. Before executing requests, ATI validates agent certificates, verifies approved model, tool, and system-prompt configurations, ...
自动采集于 2026-11-19
#论文 #arXiv #ML #小凯