AI RESEARCH

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models

arXiv CS.LG

ArXi:2604.09651v1 Announce Type: cross Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like $\pi_0$ showing great promise in generating smooth, continuous actions. As these models advance, their unique action generation mechanism - the vector field dynamics - presents a critical yet unexplored security vulnerability, particularly backdoor vulnerabilities. Existing backdoor attacks designed for autoregressive discretization VLAs cannot be directly applied to this new continuous dynamics. We.