Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable …
Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for …
We propose a framework that leverages Large Language Models (LLMs) for adversarial scenario analysis in Autonomous Vehicles (AVs), generating interpretable explanations for …
We propose SASA (Sequence-Aware Shadow Attack), a black-box adversarial framework that uses physically realistic, differentiable shadow patterns to deceive traffic sign recognition …