When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
4.00T1 sourcearXiv cs.MA
Source record
Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2607.11751.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryResearch paper showing that runtime monitors in multi-agent LLM systems can be bypassed by distributed backdoors that split harmful payloads across agents so each fragment appears benign locally. Authors prove an observability boundary theorem and demonstrate across testbeds that local monitors fail exactly when local evidence disappears.
Why it mattersIdentifies a structural blind spot in standard agent safety architecture. Anyone deploying multi-agent pipelines with step-level monitoring needs to reckon with this compositional attack class.
Cited by
No citations on record.