Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models
World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threats remains largely underexplored. We study whether a single physical adversarial texture can mislead the victim model across different real-world scenarios where observ...
Song Xia, Mei-Wen Ding, Chen-Qi Kong et al.
· 0 citations