A two-step soft-prompt backdoor attack called Robo-Troj (listed as MuTRAP on arXiv) makes LLM-based robot planners emit malicious plans when hidden trigger words are present, with near-perfect attack success.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems
A two-step soft-prompt backdoor attack called Robo-Troj (listed as MuTRAP on arXiv) makes LLM-based robot planners emit malicious plans when hidden trigger words are present, with near-perfect attack success.