Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models

ArXi:2605.25889v1 Announce Type: cross Vision-Language-Action (VLA) models are increasingly deployed on real robots, where each predicted action is executed and each failure carries a safety cost. They reach high success rates on clean inputs but collapse under small adversarial perturbations. A $16/255$ PGD attack on OpenVLA-7B drops LIBERO success from above $95\%$ to under $5\%$. Empirical defenses recover some robustness at a cost in clean accuracy, but the literature does not say whether the trade-off has a theoretical floor. We prove that it does.