SoK: On the Semantic AI Security in Autonomous Driving

arXiv:2203.05314v2 Announce Type: replace
Abstract: Autonomous Driving (AD) systems rely on AI components to make safety and correct driving decisions. Unfortunately, today's AI algorithms are known to be generally vulnerable to adversarial attacks. However, for such AI component-level vulnerabilities to be semantically impactful at the system level, it needs to address non-trivial semantic gaps both (1) from the system-level attack input spaces to those at AI component level, and (2) from AI component-level attack impacts to those at the system …

address adversarial adversarial attacks ai algorithms ai security algorithms arxiv attacks autonomous autonomous driving components cs.ai cs.cr cs.ro driving safety security semantic system systems today vulnerabilities vulnerable