HF Daily Papers
· Papers
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack
Flow-matching vision-language-action (VLA) models such as pi0 generate robot actions by integrating a learned denoising velocity field, and have been reported to resist adversarial perturbations that readily fool autoregressive VLAs. We show that this robustness is largely illusory: it stems from pr