AI RESEARCH
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
arXiv CS.AI
•
ArXi:2603.23117v2 Announce Type: cross By integrating Chain-of-Thought (CoT) reasoning, Vision-Language-Action (VLA) models have nstrated strong capabilities in robotic manipulation, particularly by improving generalization and interpretability. However, the security of CoT-based reasoning mechanisms remains largely unexplored. In this paper, we show that CoT reasoning