Speaker: Yi Zhu, Computer Science, WSU

Time: Wednesday, March 26, from 2:30 pm to 3:30 pm

Location for in-person participants: 1146 FAB 

Zoom link for online audience: https://wayne-edu.zoom.us/j/92845590121?pwd=CpRA5Wa5gzSMn2xiVkR2abD83O5nrH.1

Title: Security of AI-enabled perception systems in autonomous driving

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 is an Assistant Professor of the Department of Computer Science at Wayne State University. Before that, he obtained his Ph.D. in 2024 from the Department of Computer Science and Engineering, University at Buffalo. His research interests lie in the broad areas of Artificial Intelligence, Security & Privacy, Cyber-Physical Systems (CPS), and Internet of Things (IoT). The primary goal of his research is to build trustworthy AI-powered CPS and IoT systems. His research outcomes have been published in various top venues such as CCS, NDSS, USENIX Security, MobiCom and SenSys.

______________________________________________________________________

The CAD Seminar Series is a dedicated platform for advancing knowledge, fostering innovation, and promoting collaboration across the fields of Computation, Artificial Intelligence, and Data Science. This series brings together leading experts, researchers, and professionals to explore the latest developments, tackle emerging challenges, and drive forward-thinking solutions at the convergence of these critical disciplines.

Objectives:

• Advance Knowledge: Share cutting-edge research and insights that push the boundaries of what is known in CAD.

• Foster Innovation: Encourage the development of novel ideas and solutions through interdisciplinary dialogue and creative thinking.

• Promote Collaboration: Unite expertise across disciplines and build bridges between academia, industry, and government to address complex problems and create opportunities for joint ventures.

Target Audience: The CAD Seminar Series is designed for a diverse audience, including faculty, researchers, students, and professionals in Computation, AI, Data Science, and related fields. It serves as a forum for exchanging ideas, networking, and contributing to the growth of these rapidly evolving areas. We highly recommend in-person attendance to enhance engagement and networking opportunities with speakers and fellow participants.

Call for Participation: We welcome contributions from researchers, practitioners, and students. Whether presenting your work, participating in discussions, or attending as a learner, your involvement is crucial to the success of this collaborative initiative.