Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study
Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: several poisoned tools each hide one encrypted fragment, spreading them across several agents, and an external step reassembles and executes them after the run. Per-step safety checks that judge each action in isolation may fail to recognize the complete distributed payload. We investigate how early such an attack can be detected while the run is still unfolding, and how robustly it can be caught once its most obvious cues are stripped away. We build a working instance on a hierarchical multi-agent system, run it under benign and attacked conditions across five language models and two tool enviro...
| Authors | Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang et al. |
|---|---|
| Primary category | cs.CR |
| Published | 27 July 2026 |
| Last updated at source | 2 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.