I am Yulong Cao [cv], a research scientist at the NVIDIA Autonomous Vehicle Research group directed by Marco Pavone. My research interests span machine learning security, sensor security, and system security. My research goal is to build secure and safe autonomous driving systems that are aligned with human. I completed my Ph.D from the Computer Science and Engineering department of University of Michigan, advised by Morley Mao. Before that, I also received my B.S from both University of Michigan and Shanghai Jiao Tong University. My Ph.D works sought to understand the vulnerability status of autonomous driving systems and how to make it robust.
Internship opportunities at AVG Summer’24: if you are interested in Traffic Modeling, Trustworthy AI, please feel free to reach out or apply!
Besides research, I also find photography another lens to observe the world better. Check out my gallery or my instagram to find more!
Preprints
Wenhao Ding*, Yulong Cao*, Ding Zhao, Chaowei Xiao, Marco Pavone “RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios” [arxiv]
Yingzi Ma, Yulong Cao, Jiachen Sun, Marco Pavone, Chaowei Xiao “Dolphins: Multimodal Language Model for Driving” [arxiv]
Publications
Yulong Cao, Boris Ivanovic, Chaowei Xiao, Marco Pavone “Reinforcement Learning with Human Feedback for Realistic Traffic Simulation” (ICRA’24)
Ziyuan Zhong, Davis Rempe, Yuxiao Chen, Boris Ivanovic, Yulong Cao, Danfei Xu, Marco Pavone, Baishakhi Ray “Language-Guided Traffic Simulation via Scene-Level Diffusion” (CoRL’23, Oral)
Yulong Cao, Sri Hrushikesh Varma Bhupathiraju, Pirouz Naghavi, Takeshi Sugawara, Z. Morley Mao, Sara Rampazzi “You Can’t See Me: Physical Removal Attacks on LiDAR-based Autonomous Vehicles Driving Frameworks” (USENIX’23)
Minkyoung Cho, Yulong Cao, Zixiang Zhou, Z. Morley Mao “ADoPT: LiDAR Spoofing Attack Detection based on Point-Level Temporal Consistency” (BMVC’23)
Yulong Cao, Danfei Xu, Xinshuo Weng, Zhuoqing Mao, Anima Anandkumar, Chaowei Xiao, Marco Pavone “Robust Trajectory Prediction against Adversarial Attacks” (CoRL’22, Oral)
Yulong Cao, Chaowei Xiao, Anima Anandkumar, Danfei Xu, Marco Pavone “AdvDO: Realistic Adversarial Attacks for Trajectory Prediction” (ECCV’22)
R Spencer Hallyburton, Yupei Liu, Yulong Cao, Z Morley Mao, and Miroslav Pajic “Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous Vehicles” (USENIX’22)
Yulong Cao*, Ningfei Wang*, Chaowei Xiao*, Dawei Yang*, Jin Fang, Ruigang Yang, Qi Alfred Chen, Mingyan Liu, Bo Li “Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks” (Oakland’21) [PDF] [Website]
Jiachen Sun, Yulong Cao, Christopher Choy, Zhiding Yu, Anima Anandkumar, Z. Morley Mao, and Chaowei Xiao “Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions” (NeurIPS’21)
Jiachen Sun, Karl Koenig, Yulong Cao, Qi Alfred Chen, and Z. Morley Mao “On The Adversarial Robustness of 3D Point Cloud Classification” (BMVC’21)
Yulong Cao, Jiaxiang Ma, Kevin Fu, Sara Rampazzi, Z. Morley Mao “Automated Tracking System for LiDAR Spoofing Attacks on Moving Targets” (AutoSec’21, Best Demo Award Runner-up)
Jiachen Sun, Yulong Cao, Qi Alfred Chen, and Z. Morley Mao “Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures” (USENIX’20) [Webpage] [PDF]
Yulong Cao, Chaowei Xiao, Benjamin Cyr, Yimeng Zhou, Won Park, Sara Rampazzi, Qi Alfred Chen, Kevin Fu, and Z. Morley Mao “Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving” (CCS’19) [Webpage] [PDF] [Forbes]
Qi Alfred Chen, Matthew Thomas, Eric Osterweil, Yulong Cao, Jie You, Z. Morley Mao “Client-side Name Collision Vulnerability in the New gTLD Era: A Systematic Study” (CCS’17) [PDF]
Workshops and Posters
Yulong Cao, Jiachen Sun, Chaowei Xiao, Qi Alfred Chen, Z. Morley Mao “Delving into the Remote Adversarial Patch in Semantic Segmentation” Posters at ICML 2021 Workshop on Socially Responsible Machine Learning. July. 2021.
Yanan Guo, Christopher Joseph, Takami Sato, Yulong Cao, Qi Alfred Chen, Yueqiang Cheng “An Adversarial Attack on DNN-based Adaptive Cruise Control Systems” Posters at ICCV 2021 Workshop on Adversarial Robustness In the Real World. Oct 11, 2021.
Yulong Cao*, Ningfei Wang*, Chaowei Xiao*, Dawei Yang*, Jin Fang, Ruigang Yang, Qi Alfred Chen, Mingyan Liu, Bo Li “Demonstration: 3D Adversarial Object against MSF-based Perception in Autonomous Driving” The 3rd Conference on Machine Learning and Systems (MLSys 2020) Demonstration Track
Mentored Students
Talks
Guest Lecture at UW-Madison: Secure and Safe Autonomous Driving System