一作ACL 2026Findings· Findings of ACL
S ilent D rift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
Bingxin Xu · Yuzhang Shang · Binghui Wang · Emilio Ferrara
摘要
Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundamental security flaw in modern VLA systems: the combination of action chunking and delta pose representations creates...