A single compromised robot can propagate malicious intent via inter-robot communication to produce coordinated unsafe actions across an entire LLM-planned multi-robot system.
Don’t listen to me: Understanding and exploring jailbreak prompts of large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Propagating Unsafe Actions in LLM Controlled Multi-Robot Collaboration via Single Robot Compromise
A single compromised robot can propagate malicious intent via inter-robot communication to produce coordinated unsafe actions across an entire LLM-planned multi-robot system.