Embodied Adversarial Attack: A Dynamic Robust Physical Attack in Autonomous Driving

arXiv:2312.09554v2 Announce Type: replace
Abstract: As physical adversarial attacks become extensively applied in unearthing the potential risk of security-critical scenarios, especially in autonomous driving, their vulnerability to environmental changes has also been brought to light. The non-robust nature of physical adversarial attack methods brings less-than-stable performance consequently. To enhance the robustness of physical adversarial attacks in the real world, instead of statically optimizing a robust adversarial example via an off-line training manner like the existing methods, this paper proposes a …

abstract adversarial adversarial attacks arxiv attack methods attacks autonomous autonomous driving become cs.cv driving dynamic embodied environmental light nature performance risk robust security type vulnerability