Speaker

Dr. Yi Zhu, Department of Computer Science, Wayne State University

Abstract

Autonomous vehicles (AVs) are visioned as a revolutionary power for future transportation. A fundamental function of AV systems is perception, which aims to understand the surrounding driving environment using the sensors such as cameras, radar, and LiDAR, to help the AVs make critical driving decisions. However, some attackers may perform malicious attacks and manipulate the victim AV's perception results, aiming to cause accidents to hurt a specific target, commit insurance fraud, or raise safety concerns on a specific model of AV in order to defame an autonomous driving company. The presence of these malicious attacks can largely degrade the safety and reliability of autonomous driving systems, which has a direct correlation with not only the safety of all road users but also the reputation of autonomous driving companies. In this talk, I will first explore the malicious attacks against individual sensors in autonomous vehicles including LiDAR and radar. Then I will present my recent study on attacking multi-sensor fusion-based perception system that employ all three types of sensors including camera, lidar and radar. In closing, I will outline future research directions on addressing the security and reliability challenges in autonomous vehicles.

Bio

Yi Zhu earned his Ph.D. in 2024 from the Department of Computer Science and Engineering, University at Buffalo. He was also a visiting scholar at Purdue University. His research interests lie in the broad areas of security, machine learning, and cyber-physical systems, with a current focus on the security of the adopted machine learning models in autonomous vehicles. His research outcomes have been published in various top venues such as CCS, NDSS, MobiCom and SenSys. He was awarded as a Presidential Fellow at the University at Buffalo.