3243 Donald Bren Hall
Irvine, CA 92697
I am a 5-th year CS Ph.D. candidate at UC Irvine working with Prof. Qi Alfred Chen.
My research interest is Cyber-Physical Systems security with a focus on autonomous driving and intelligent transportation systems security. Recently, I have been mainly working on the security of production-grade autonomous driving systems, including those providing different levels of driving autonomy (e.g., Level-2 and Level-4). Previously, I have also explored other security areas such as compiler-assisted countermeasures for fault and side-channel attacks and efficient isolation for Linux kernel subsystems.
Before joining UCI, I graduated with a M.S. and B.E. from North Carolina State Univerity, Raleigh and Hangzhou Dianzi University, China, respectively.
|Oct 31, 2020||Serving as the Web Chair for IEEE Workshop on the Internet of Safe Things (SafeThings 2021) co-located with IEEE S&P 2021. [Call for papers, Due: Jan 25 2021, AoE]|
|Sep 27, 2020||Led the ASGuard team won the Championship out of 24 participating teams in the world’s first Autonomous Driving CTF competition hosted by Baidu Security! Big congrats, Takami, Ningfei, Ziwen, Yunpeng, and Zeyuan!|
|Sep 10, 2020||
Serving as a PC member for DYnamic and Novel Advances in Machine Learning and Intelligent Cyber Security (DYNAMICS) Workshop co-located with ACSAC 2020. Please consider submitting your papers! [Call for papers, Due: Oct
|Sep 3, 2020||Serving as a reviewer for ICLR 2021.|
- arXivHold Tight and Never Let Go: Security of Deep Learning based Automated Lane Centering under Physical-World AttackarXiv:2009.06701 2020
- USENIX SecurityDrift with Devil: Security of Multi-Sensor Fusion based Localization in High-Level Autonomous Driving under GPS SpoofingIn USENIX Security Symposium (USENIX Security) 2020 (Winter quarter acceptance rate 13.0% = 62/477)
- ICSEA Comprehensive Study of Autonomous Vehicle BugsIn ACM/IEEE International Conference on Software Engineering (ICSE) 2020 (Acceptance rate 23.5% = 129/550)
- ICLRFooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object TrackingIn International Conference on Learning Representations (ICLR) 2020 (Acceptance rate 26.5% = 687/2594)