Project Grant 2235231

This $700,000 Project Grant awarded by the National Science Foundation (NSF) Division of Computing and Communication Foundations supports research at Michigan State University to enhance the security and robustness of autonomous driving systems against physical-world perceptual illusion attacks. The project aims to develop advanced sensing and learning technologies that can effectively detect and mitigate malicious attempts to create false perceptions that could undermine the safety of autonomous vehicles. Key research focus areas include: (1) a comprehensive framework to evaluate vulnerabilities and devise attack vectors for generating deceptive perceptions, (2) a real-time super-resolution radar sensing system and data fusion approach to bolster sensor robustness, and (3) a systematic framework for achieving robust multi-modal perception against attacks using representation learning. The solutions will undergo rigorous simulation and experimental testing to validate their effectiveness in real-world scenarios. This research supports the NSF's CISE program goals to advance secure and reliable autonomous driving technologies, while also providing training opportunities for underrepresented students.