COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks

arXiv:2403.02329v1 Announce Type: cross
Abstract: Multi-sensor fusion systems (MSFs) play a vital role as the perception module in modern autonomous vehicles (AVs). Therefore, ensuring their robustness against common and realistic adversarial semantic transformations, such as rotation and shifting in the physical world, is crucial for the safety of AVs. While empirical evidence suggests that MSFs exhibit improved robustness compared to single-modal models, they are still vulnerable to adversarial semantic transformations. Despite the proposal of empirical defenses, several works show that …

adversarial arxiv attacks autonomous autonomous vehicles commit cs.cr cs.cv cs.lg fusion physical play robustness role rotation safety semantic sensor systems vehicles world