Shaoyuan Xie

Shaoyuan Xie

I am a Ph.D. student in the Donald Bren School of Information and Computer Sciences at University of California, Irvine advised by Prof. Alfred Chen. I received my B.Eng. degree in Automation at Huazhong University of Science and Technology.

My research focuses on the intersection of Machine Learning, Security, and Cyber-Physical System (e.g., autonomous vehicles, drones), highlighting the security, robustness, and reliability of AI systems in the physical world.

Email / CV / Google Scholar / Twitter / Github

News

[01/2025] - One paper is accepted by ICLR 2025.

[08/2024] - One paper is accepted by NDSS 2025.

[12/2023] - One paper is accepted by TMLR.

[11/2023] - We are hosting The RoboDrive Challenge at ICRA 2024.

[09/2023] - One paper is accepted by NeurIPS 2023.

[06/2023] - I will join OpenMMLab at Shanghai AI Lab as an intern , during summer 2023.

[03/2023] - I will join University of California, Irvine in 2023 Fall as a PhD student in Computer Science.

[11/2022] - We are organizing the RoboDepth Competition at ICRA 2023.

[05/2022] - I will join CCVL at Johns Hopkins University as a research intern, during summer 2022.

Publications

	FlyTrap: Physical Distance-Pulling Attack Towards Camera-based Autonomous Target Tracking Systems Shaoyuan Xie, Mohamad Fakih, Fayzah Alshammari, Ningfei Wang, Junchi Lu, Takami Sato, Halima Bouzidi, Mohammad Al Faruque, Qi Alfred Chen Under review project
	Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives Shaoyuan Xie, Lingdong Kong, Yuhao Dong, Chonghao Sima, Wenwei Zhang, Qi Alfred Chen, Ziwei Liu, Liang Pan Preprint, 2025 paper / code / project
	Exploring Backdoor Attacks against Large Language Model-based Decision Making Ruochen Jiao, Shaoyuan Xie, Justin Yue, Takami Sato, Lixu Wang, Yixuan Wang, Qi Alfred Chen, Qi Zhu * Equal Contribution International Conference on Learning Representations (ICLR), 2025 paper / code / project
	Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective Ningfei Wang, Shaoyuan Xie, Takami Sato, Yunpeng Luo, Kaidi Xu, Qi Alfred Chen Network and Distributed System Security Symposium (NDSS), 2025 paper / code / project
	Benchmarking Out-of-Distribution Depth Estimation under Corruptions Lingdong Kong, Shaoyuan Xie, Hanjiang Hu, Benoit Cottereau, Lai Xing Ng, Wei Tsang Ooi Conference on Neural Information Processing Systems (NeurIPS), 2023 paper / code / project
	Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving Shaoyuan Xie, Lingdong Kong, Wenwei Zhang, Jiawei Ren, Liang Pan, Kai Chen, Ziwei Liu IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) paper / code / project
	On the Adversarial Robustness of Camera-based 3D Object Detection Shaoyuan Xie, Zichao Li, Zeyu Wang, Cihang Xie Transactions on Machine Learning Research (TMLR), 2023 paper / code

Workshop Organizer

	The RoboDrive Challenge ICRA Workshop, 2024 technique report / website
	The RoboDepth Challenge ICRA Workshop, 2023 technique report / website

Experience

Research Intern, OpenMMLab, June 2023-Aug 2023, Advisor: Wenwei Zhang

Research Intern, JHU & UCSC, Summer 2022, Advisor: Cihang Xie

Honors and Awards

Dean's Fellowship, UC Irvine, 2023.

Honours Degrees, HUST (Top 3%), 2023.

National Scholarship, (Top 0.2% national-wide), 2020 and 2021.

Outstanding Undergraduate Student, HUST (Top 1%), 2020.

Misc

Conference Reviewer: CVPR, IEEE S&P, ACM CCS
Journal Reviewer: ISPRS J. Photogramm. Remote Sens

Stolen from Jon Barron