Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
Abstract
AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential for AI's task generalization but enable new threats like secret collusion and coordinated swarm attacks. Network effects can rapidly spread privacy breaches, disinformation, jailbreaks, and data poisoning, while multi-agent dispersion and stealth optimization help adversaries evade oversight - creating novel persistent threats at a systemic level. Despite their critical importance, these security challenges remain understudied, with research fragmented across disparate fields including AI security, multi-agent learning, complex systems, cybersecurity, game theory, distributed systems, and technical AI governance. We introduce multi-agent security, a new field dedicated to securing networks of AI agents against threats that emerge or amplify through their interactions - whether direct or indirect via shared environments - with each other, humans, and institutions, and characterise fundamental security-utility and security-security trade-offs across both distributed and decentralised settings. Our preliminary work (1) taxonomizes the threat landscape arising from interacting AI agents, (2) offers applications to multi-agent security for work across diffuse subfields, and (3) proposes a unified research agenda addressing open challenges in designing secure agent systems and interaction environments. By identifying these gaps, we aim to guide research in this critical area to unlock the socioeconomic potential of large-scale agent deployment, foster public trust, and mitigate national security risks in critical infrastructure and defense contexts.
Cite
@article{arxiv.2505.02077,
title = {Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents},
author = {Christian Schroeder de Witt and Klaudia Krawiecka and Igor Krawczuk and Ben Hagag and William L. Anderson and Peter Belcak and Ben Bucknall and Xiaohong Cai and Ayush Chopra and Doron Cohen and Ron F. Del Rosario and Andis Draguns and Annie Gray and Keren Katz and Vasilios Mavroudis and Jaron Mink and Sumeet Ramesh Motwani and Jonathan Petit and Leif-Sebastian Rembeck and Chandler Smith and John Sotiropoulos and Steven Young and Sarah Scheffler and Mary Llewellyn},
journal= {arXiv preprint arXiv:2505.02077},
year = {2026}
}