Communication attacks on LLM-controlled multi-robot teams succeed across all three tested architectures, and a lightweight provenance-verification gate cuts the violation rate roughly in half.
Large language models as generalizable policies for embodied tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems
Communication attacks on LLM-controlled multi-robot teams succeed across all three tested architectures, and a lightweight provenance-verification gate cuts the violation rate roughly in half.