Backdoor attacks aligned with JSON command formats in LLM robot controllers achieve 83% attack success rate while preserving over 93% clean accuracy and sub-second latency.
Exploring the adversarial vulnerabilities of vision-language-action models in robotics
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
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems
Backdoor attacks aligned with JSON command formats in LLM robot controllers achieve 83% attack success rate while preserving over 93% clean accuracy and sub-second latency.