English

Optimally Auditing Adversarial Agents

Computer Science and Game Theory 2026-04-29 v1 Artificial Intelligence Computers and Society

Abstract

Fraud can pose a challenge in many resource allocation domains, including social service delivery and credit provision. For example, agents may misreport private information in order to gain benefits or access to credit. To mitigate this, a principal can design strategic audits to verify claims and penalize misreporting. In this paper, we introduce a general model of audit policy design as a principal-agent game with multiple agents, where the principal commits to an audit policy, and agents collectively choose an equilibrium that minimizes the principal's utility. We examine both adaptive and non-adaptive settings, depending on whether the principal's policy can be responsive to the distribution of agent reports. Our work provides efficient algorithms for computing optimal audit policies in both settings and extends these results to a setting with limited audit budgets.

Keywords

Cite

@article{arxiv.2604.25085,
  title  = {Optimally Auditing Adversarial Agents},
  author = {Sanmay Das and Fang-Yi Yu and Yuang Zhang},
  journal= {arXiv preprint arXiv:2604.25085},
  year   = {2026}
}

Comments

Published in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026, pages 16787-16794