Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for …
Adversarial patches pose a practical threat to modern object detectors. Prior work shows vulnerability, but three gaps limit actionable insight: (i) few score-based black-box …
Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable …
We propose SASA (Sequence-Aware Shadow Attack), a black-box adversarial framework that uses physically realistic, differentiable shadow patterns to deceive traffic sign recognition …
We present a framework for black-box adversarial attacks on traffic signs using dynamic, temporally coherent shadows. Unlike prior work that focuses on single-image attacks or …