ATI 联邦架构:为跨组织 AI 智能体补上身份与信任层
Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents
做跨组织智能体协作的团队值得看看这篇:ATI 不改模型,外挂一层就能验证对方智能体的身份、配置和完整性,14 种攻击场景下遏制率从 43% 拉到 84%,每请求只多 174 微秒,还是开源的。
arXiv 论文提出 Agent Trust Infrastructure(ATI),一个基于 PKI、零信任架构(ZTA)和远程证明的智能体安全架构,解决跨组织智能体缺乏统一身份验证与授权机制的问题。ATI 通过各组织的对等证书机构(AgentCA)建立联邦信任,无需共享根权威;在执行请求前校验智能体证书、核对已批准的模型、工具和 system-prompt 配置,并执行三项授权策略检查。
实现上,ATI 作为外部安全执行层接入现有智能体框架,不修改底层模型,身份与请求验证采用 IETF WIMSE workload token 格式,模型、工具和 system-prompt 的完整性验证使用 Entity Attestation Tokens。在 8 个组织、6 个智能体框架、每组织 5 个智能体的模拟联邦中评估,覆盖 14 种攻击场景和 6 个良性任务,涉及 5 个智能体模型,用评审模型面板判定结果。
开启全部执行机制后,攻击遏制率从 43% 提升到 84%(11 个一致评估场景下为 40% 到 80%),每请求开销约 174 微秒。ATI 已开源,可作为独立包与主流智能体框架配合使用,适合需要在组织间部署智能体协作的企业安全团队评估。
Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents
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, and enforces authorization through three policy checks. We implement ATI as an external security enforcement layer that integrates with existing agent frameworks without modifying their underlying models. We evaluate ATI in a simulated federation of eight organizations using six agent frameworks, each deploying a five-agent team. Security experiments involve two organizations and assess 14 attack scenarios and six benign tasks across five agent models, using five attack variations and three repetitions per variation. A panel of judge models evaluates the experimental outcomes. With all enforcement mechanisms enabled, attack containment increases from 43% to 84% (40% to 80% for the 11 attack scenarios evaluated consistently across all configurations), while enforcement introduces approximately 174 microseconds of overhead per request. ATI is released as an open-source, framework-independent package that uses IETF WIMSE workload token formats for identity and request verification and Entity Attestation Tokens for model, tool, and system-prompt integrity verification.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:ATI、PKI、零信任架构、智能体,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Viet K. Nguyen, Mohammad I. Husain),经 AITOP 多维评分管线结构化提炼。