paperApril 2025Unreviewed

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats

L'eo Boisvert, Mihir Bansal, Chandra Kiran Reddy Evuru, Gabriel Huang, Abhay Puri, Avinandan Bose, Maryam Fazel, Quentin Cappart, Jason Stanley, Alexandre Lacoste, Alexandre Drouin, K. Dvijotham

arXiv.org

View resource

Abstract

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic agentic frameworks like BrowserGym (for web agents) and $\tau$-bench (for tool calling agents); 2) It is configurable and allows for detailed threat modeling, allowing configuration of specific components of the agentic framework being attackable, and specifying targets for the attacker; and 3) It is modular and decouple

Cite

@misc{boisvert2025doomarena,
  title = {{DoomArena: A framework for Testing AI Agents Against Evolving Security Threats}},
  author = {L'eo Boisvert and Mihir Bansal and Chandra Kiran Reddy Evuru and Gabriel Huang and Abhay Puri and Avinandan Bose and Maryam Fazel and Quentin Cappart and Jason Stanley and Alexandre Lacoste and Alexandre Drouin and K. Dvijotham},
  year = {2025},
  month = apr,
  eprint = {2504.14064},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2504.14064},
  url = {https://www.semanticscholar.org/paper/9e85ce8f1822105251870493e5326468fba18f0d}
}