Collaborative Research: SaTC: CORE: Small: NSF-DST: Towards Secure and Resilient Collaborative Autonomous Driving (CoAD)

Suny At Buffalo, Amherst NY

Investigators

Abstract

This project aims to investigate both the security and robustness of Collaborative Autonomous Driving (CoAD) to improve the safety and resiliency of connected and autonomous vehicles (CAVs). Despite being an emergent trend, CoAD systems, consisting of collaborative CAVs and Roadside Units (RSUs), are a new type of cyber-physical systems (CPS) that have received little attention in the research community, especially in terms of their security and resiliency. To conduct the proposed research, the proposers will build upon the team’s complementary expertise in a wide range of topics including vehicle security, Vehicle-to-Everything (V2X) security, adversarial attacks to the Artificial Intelligence (AI)-powered perception subsystem, formal methods and verification, robust control, and end-to-end evaluation. The project will take a systematic approach and develop a comprehensive framework when examining new attack vectors/surfaces in the CoAD systems, and propose novel mitigation and defense mechanisms. is an integrated effort by two PIs from the University at Buffalo (UB), and UC Irvine (UCI) from the US side, and two PIs from the Indian Institute of Technologies (IIT) at Kharagpur (IIT-KGP) and Jodphur (IIT-J) from the India side. The project is expected to result in joint publications as a part of dissemination efforts, joint mentoring of students by the US and India PIs, and new datasets, as well as increased public awareness of cyber-security threats and trust in the resilience of autonomous driving. In addition, new course and publicly available materials based on research results will be developed to attract and train students, including under underrepresented minority students. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.