Seven security challenges in cross-domain multi-agent LLM systems
Large language models are evolving into autonomous agents that collaborate across organizations for tasks like disaster response and supply-chain optimization. However, such cooperation breaks unified trust assumptions: a benign agent may leak secrets or violate policy when interacting with untrusted peers. This paper maps the security agenda for cross-domain multi-agent LLM systems, introducing seven categories of novel challenges alongside plausible attacks, evaluation metrics, and research directions.
Authors
- Ronny Ko (ORCID: https://orcid.org/0000-0002-1282-5208)
- Makoto Onizuka (ORCID: https://orcid.org/0000-0001-5559-8300)
- Shuyuan Zheng (ORCID: https://orcid.org/0000-0002-1835-3424)
- Chuan Xiao (ORCID: https://orcid.org/0000-0001-6599-8762)
- J Chung
- Won-Yong Shin
- Tae-Wan Kim
Institutions
- Seoul National University (KR)
- Yonsei University (KR)
- Sensor Electronics (United States) (US)
- The University of Osaka (JP)
Publication Details
- Journal
- npj Artificial Intelligence
- Published
- 2026-06-13
- DOI
- https://doi.org/10.1038/s44387-026-00128-9
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00