DTP-Attack: A decision-based black-box adversarial attack on trajectory prediction
Li, Jiaxiang, Jun Yan, Daniel Watzenig, and Huilin Yin. "DTP-Attack: A decision-based black-box adversarial attack on trajectory prediction." In ICRA. 2026.
CV
Education
- Ph.D. in AI, Tongji University, 2025
- M.S. in EE, Tongji University, 2012
- B.S. in EE, Shanghai Jiaotong University, 2009
Work experience
- From Winter 2025: Lecturer at Shanghai Ocean University
- Trustworthy AI research
- Research on intelligent marine and aquatic devices
- Fall 2024-Summer 2025: Visiting Scientist at Shandong University
- Design on sports robots and humanoids
- Co-supervise Ph.D. students for academic research
- Fall 2012-Summer 2020: Engineer
- Software design
- Machine learning algorithm design
Skills
- Wavelet Theorty
- Differential Geometry
- Information Theory
Publications
AMRM-Pure: Semantic-Preserving Adversarial Purification
Zhihao Dou, Zhiqiang Gao, Dongfei Cui, Weida Wang, Qinjian Zhao, Dinggen Zhang, Jun Yan, Zeke Xie, Shufei Zhang. "AMRM-Pure: Semantic-Preserving Adversarial Purification." In AISTATS. 2026.
Certified Robustness in Automated Driving Perception: A Review
Yin, Huilin, Ziming Zhao, Jun Yan, and Daniel Watzenig. "Certified Robustness in Automated Driving Perception: A Review: H. Yin et al." Automotive Innovation (2025): 1-21.
Exploring Causal Information Bottleneck for Adversarial Defense
Yan, Jun, Huan Hua, Weiquan Huang, Xi Fang, Wancheng Ge, Jiancheng Yang, and Yongwei Wang. "Exploring Causal Information Bottleneck for Adversarial Defense." IEEE Transactions on Information Forensics and Security (2025).
MV-BMR: A Real-time Motion and Vision Sensing Integration based Agile Badminton Robot
Shi, Zhiwei, Xingyu Zhang, Chengxi Zhu, Haochen Wang, Jun Yan, Fan Yang, and Dong Xuan. "MV-BMR: A Real-time Motion and Vision Sensing Integration based Agile Badminton Robot." Information Fusion (2025): 103337.
Spectral Scaling-Based Augmentation for Corruption-Robust Image Classification
Zhang, Zhuang, Lijun Zhang, Dejian Meng, Wei Tian, and Jun Yan. "Spectral Scaling-Based Augmentation for Corruption-Robust Image Classification." IEEE Signal Processing Letters (2025).
Sparse Query Dense: Enhancing 3D Object Detection with Pseudo Points
Mo, Yujian, Yan Wu, Junqiao Zhao, Zhenjie Hou, Weiquan Huang, Yinghao Hu, Jijun Wang, and Jun Yan. "Sparse Query Dense: Enhancing 3D Object Detection with Pseudo points." In Proceedings of the 32nd ACM International Conference on Multimedia, pp. 409-418. 2024.
Segment-anything models achieve zero-shot robustness in autonomous driving
Yan, Jun, Pengyu Wang, Danni Wang, Weiquan Huang, Daniel Watzenig, and Huilin Yin. "Segment-anything models achieve zero-shot robustness in autonomous driving." In 2024 IEEE International Automated Vehicle Validation Conference (IAVVC), pp. 1-8. IEEE, 2024.
Pcqa: A strong baseline for aigc quality assessment based on prompt condition
Fang, Xi, Weigang Wang, Xiaoxin Lv, and Jun Yan. "Pcqa: A strong baseline for aigc quality assessment based on prompt condition." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6167-6176. 2024.
Enhance adversarial robustness via geodesic distance
Yan, Jun, Huilin Yin, Ziming Zhao, Wancheng Ge, and Jingfeng Zhang. "Enhance adversarial robustness via geodesic distance." IEEE Transactions on Artificial Intelligence 5, no. 8 (2024): 4202-4216.
Talks
Talk on Adversarial Robustness
Talk at Training for public functionaries, Online at Tongji University, China, China
Talk on Safe and Secure Embodied Systems
Talk at GDPS-2025, Zhangjiang, Shanghai
Adversarial Examples: Theory, Methods, and Evaluation Benchmarks
Talk at Seminars of Cybersecurity School, Jinan University (Guangzhou), Online
Talk on SOTIF of Autonomous Driving
Talk at Training for public functionaries, Jirenlou Building of Jiading Campus at Tongji University, China, China
Talk on Humanoids
Talk at Training for public functionaries, Shangyu, Shaoxing, China
Tutorial 1 on Optimization for Deep Learning
Tutorial at Seminars hosted by Prof. Xiaoyang Chen on AI for Math and Math for AI, Online
Teaching
Service and leadership
- Currently signed in to 43 different slack teams