# Optimally Auditing Adversarial Agents

arXiv: https://arxiv.org/abs/2604.25085 · HTML: https://mlsanity.com/paper/2604.25085/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [Strategic Classification from Revealed Preferences](https://mlsanity.com/paper/1710.07887/) (2017)
- [Incentivizing Truthfulness Through Audits in Strategic Classification](https://mlsanity.com/paper/2012.09147/) (2020)
- [Audit Games with Multiple Defender Resources](https://mlsanity.com/paper/1409.4503/) (2014)
- [Catch Me If You Can: Combatting Fraud in Artificial Currency Based Government Benefits Programs](https://mlsanity.com/paper/2402.16162/) (2024)
- [Learning to Play Multi-Follower Bayesian Stackelberg Games](https://mlsanity.com/paper/2510.01387/) (2025)

## Abstract (arXiv)

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.