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

arXiv:2403.02329v1 Announce Type: new
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 …

abstract adversarial arxiv attacks autonomous autonomous vehicles cs.cr cs.cv cs.lg fusion modern perception robustness role rotation safety semantic sensor systems type vehicles vital world