跳到正文
arXiv cs.AI· Viet K. Nguyen, Mohammad I. Husain·· 2 小时前AI 评分42

Agent Trust Infrastructure (ATI):跨组织自主 AI 智能体的联邦身份、信任、证明与问责架构

Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents

AI 导读

研究者提出 Agent Trust Infrastructure(ATI),一个基于 PKI、零信任架构和远程证明、与框架无关的跨组织 AI 智能体安全架构。在 8 个组织、6 种智能体框架的模拟联邦中测试 14 种攻击场景,启用全部执行机制后攻击遏制率从 43% 提升至 84%,每请求仅增加约 174 微秒开销。

正文 · 原文

View PDF HTML (experimental)

Abstract: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.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.23202 [cs.AI]
  (or arXiv:2611.23202v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23202

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mohammad I. Husain [view email]
[v1] Tue, 17 Nov 2026 18:44:25 UTC (843 KB)

来源:arXiv cs.AI · arxiv.org