CRAIMAMay 15

Who Owns This Agent? Tracing AI Agents Back to Their Owners

arXiv:2605.1603560.3
Predicted impact top 23% in CR · last 90 daysOriginality Highly original
AI Analysis

This work addresses the critical accountability gap for AI agents, providing a practical solution for vendors to identify the account behind harmful agent behavior, which is essential for safety and security in autonomous systems.

The paper formalizes the problem of agent attribution—linking an observed AI agent interaction to the responsible account at the hosting vendor—and presents a canary-based protocol that reliably traces agents back to their owners, even under adversarial conditions where operators filter or paraphrase content.

AI agents are increasingly deployed to act autonomously in the world, yet there is still no reliable way to trace a harmful agent back to the account that deployed it. This creates the same accountability gap across both ends of the intent spectrum: benign operators may deploy misconfigured or overbroad agents that cause harm unintentionally, while malicious operators may deliberately weaponize agents for scams, harassment, or cyber attacks. In many cases, these agents are powered by vendor-hosted models, a dependency that holds even for sophisticated adversaries such as state actors conducting cyber operations. In either case, affected parties can observe the behavior but cannot notify the responsible operator, stop the session, or identify the account for investigation. We formalize this gap as the problem of agent attribution: linking an observed agent interaction to the responsible account at the hosting vendor. To our knowledge, this is the first work to define the problem and present a practical solution. Our protocol is canary-based: an authorized party injects a canary into the agent's interaction stream, and the vendor searches a narrow window of session logs to recover the originating session and account. Simple canaries suffice in non-adversarial settings. For adversarial operators who filter or paraphrase incoming content, we develop robust canary constructions that cannot be suppressed without degrading the agent's own task performance, yielding a formal asymmetry in the defender's favor. We evaluate a variety of scenarios including real-world agents and show that our attribution method is reliable, robust, and scalable for vendor-side deployment.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes