PAuth - Precise Task-Scoped Authorization For Agents
Reshabh K Sharma, Linxi Jiang, Zhiqiang Lin, Shuo Chen

TL;DR
PAuth introduces a novel authorization model for AI agents that ensures only the specific operations needed for a user's task are permitted, improving security and precision over existing broad permission systems.
Contribution
The paper proposes PAuth, a new implicit authorization model with symbolic specifications and verification mechanisms, enabling precise, task-specific permissions for AI agents.
Findings
PAuth successfully executes tasks without overprivilege in benign scenarios.
PAuth detects and warns about unauthorized operations in attack scenarios.
The model maintains low token costs while ensuring precise permission enforcement.
Abstract
The emerging agentic web envisions AI agents that reliably fulfill users' natural-language (NL)-based tasks by interacting with existing web services. However, existing authorization models are misaligned with this vision. In particular, today's operator-scoped authorization, exemplified by OAuth, grants broad permissions tied to operators (e.g., the transfer operator) rather than to the specific operations (e.g., transfer $100 to Bob) implied by a user's task. This will inevitably result in overprivileged agents. We introduce Precise Task-Scoped Implicit Authorization (PAuth), a fundamentally different model in which submitting an NL task implicitly authorizes only the concrete operations required for its faithful execution. To make this enforceable at servers, we propose NL slices: symbolic specifications of the calls each service expects, derived from the task and upstream results.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAccess Control and Trust · Scientific Computing and Data Management · Web Application Security Vulnerabilities
