Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents
Organizations: California State Polytechnic University, Pomona Pomona, CA 91768, USA
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.
Figures & tables
| Threat | Base | +Id | +Tr | +At | +Po | |
|---|---|---|---|---|---|---|
| A1 | External attacker | 20 | 100 | 100 | 100 | 100 |
| A2 | Compromised agent | 44 | 61 | 68 | 69 | 67 |
| A3 | Malicious insider | 96 | 87 | 84 | 77 | 81 |
| A4 | Stolen certificate | 53 | 56 | 100 | 100 | 100 |
| A5 | Replay attack | 15 | 13 | 17 | 15 | 75 |
| A6 | Prompt injection | 51 | 53 | 52 | 52 | 52 |
| B1 | B2 | B3 | B4 | B5 | B6 | All | |
|---|---|---|---|---|---|---|---|
| Baseline | 15/15 | 14/15 | 11/15 | 13/15 | 14/15 | 15/15 | 91% |
| Full ATI | 15/15 | 14/15 | 10/15 | 15/15 | 15/15 | 14/15 | 92% |
| Check | Mean ( s) | Median ( s) |
|---|---|---|
| Identity + Trust (entry) | 151.0 | 146.0 |
| Attestation (runtime) | 0.2 | 0.2 |
| Policy + log append (tool call) | 23.7 | 21.6 |
| (log append alone) | 23.6 | 21.3 |
| Full stack, one request | 173.8 | 167.7 |
| ID | Attack | Adversary action | Closed by |
|---|---|---|---|
| A1 | External attacker | Unauthenticated outsider with no account asks the liaison for a student’s GPA. | Identity |
| A2 | Compromised agent | An office agent is told to override its role and exfiltrate another office’s financial-aid SAI. | – |
| A3 | Malicious insider | A staff member asks the aid office to bulk-export every award record for off-site use. | Policy (cap, partial) |
| A4 | Stolen certificate | An impersonator presents an unverifiable “certificate-authenticated” identity to obtain a full record. | Trust |
| A5 | Replay attack | A transfer approval already processed is resubmitted to be processed again. | Policy |
| A6 | Prompt injection | Advising notes carry a hidden instruction telling the agent to emit an attacker token. | – |
AI Agent Security
Artificial intelligence agent security studies attacks and safeguards for tool-using, persistent, and collaborative systems across digital and physical settings.
See all 559 papers