Session – Cloud Infrastructure and Information Security
Towards Secure and Robust Autonomy Software in Autonomous Driving
Department of Computer Science
University of California, Irvine
Irvine, CA 92617
Qi Alfred Chen is an Assistant Professor in the Department of Computer Science at the University of California, Irvine. His research interest spans software security, systems security, and network security. Currently, his research focuses on security problems in autonomous systems and IoT (e.g., autonomous driving and intelligent transportation). His major research theme is addressing security challenges through systematic problem analysis and defense designs. His research has discovered and/or addressed security problems in a wide range of systems such as autonomous driving systems, next-generation transportation systems, smartphone OSes, network protocols, DNS, GUI systems, and access control systems. These works have high impacts in both academic and industry with over 25 research papers in top-tier venues in areas ranging from security, mobile systems, transportation, software engineering, to machine learning; a nationwide USDHS US-CERT alert, and multiple CVEs; over 50 news articles by major news media such as Forbes, Fortune, and BBC News; and email acknowledgments from USDOT, Apple, Microsoft, Comcast, Daimler, etc. Chen received his Ph.D. from the University of Michigan in 2018.
Autonomous Driving (AD) technology has always been an international pursuit due to its significant benefit in driving safety, efficiency, and mobility. Over 15 years after the first DARPA Grand Challenge, its development and deployment are becoming increasingly mature and practical, with some AD vehicles already providing services on public roads (e.g., Google Waymo One in Phoenix and Baidu Apollo Go in China). In AD technology, the autonomy software stack, or the AD system, is highly security-critical: it is in charge of safety-critical driving decisions such as collision avoidance and lane keeping, and thus any security problems in it can directly impact road safety. In this talk, I will describe my recent research that initiates the first systematic effort towards understanding and addressing the security problems in production AD systems. I will be focusing on two critical modules: perception and localization, and talk about how we are able to discover novel and practical sensor/physical-world attacks that can cause end-to-end safety impacts such as crashing into obstacles or driving off road. I will conclude with our current efforts on the defense side, and also discuss future research directions.