Jiachen Sun Ph.D. Candidate Computer Science and Engineering, University of Michigan, Ann Arbor

Introduction

 

I will join TikTok (San Jose) as a machine learning scientist working on responsible recommendation this Dec. I'm a 2nd-year 3rd-year 4th-year 5th-year Ph.D. candidate [CV] in Computer Science and Engineering at the University of Michigan supervised by Professor Z. Morley Mao. I got my bachelor degree from Zhiyuan College at Shanghai Jiao Tong University advised by Professor Xiaohua Tian. I had a happy time working at DiDi AI Lab as an algorithm engineer intern during my senior year under the supervision of Professor Jieping Ye. I was also fortunate to work with Professor Haitham Hassanieh as a research intern at the University of Illinois Urbana-Champaign in the summer of 2017. I spent my summer semester of 2016 as an exchange student at the University of Washington. My research interests are broadly in deep learning, computer vision, cyber-physical security, and machine learning systems, with a current focus on adversarial machine learning and trustworthy AI. I joined Uber Marketplace Pricing team an Ph.D. research MLE intern in the summer of 2023 working on product-level deep learning model robustness. I joined Meta/Facebook AI as a research intern in the summer of 2022 mentored by Dr. Caner Hazirbas and Dr. Ivan Evtimov, focusing AI integrity and out-of-distribution robustness. I interned at Lawrence Livermore National Laboratory (LLNL) in the summer of 2021 supervised by Dr. Bhavya Kailkhura and Dr. Pin-Yu Chen on the topic of certified adversarial robustness in deep learning. I also closely work with Professor Chaowei Xiao from ASU and NVIDIA Research who has been supporting my research since 2020.

 

Education

 

Sept. 2018 - now                Ph.D. in Computer Science and Engineering, University of Michigan - Ann Arbor, USA

Sept. 2014 - June 2018       B.S.E. in Information Engineering, Shanghai Jiao Tong University, China

June. 2016 - Aug. 2016       Exchange Student at Electrical & Computer Engineering, University of Washington - Seattle, USA

 

Publications

 

• [ Pre-print ] CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
  Jiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash, Z. Morley Mao, and Chaowei Xiao
  

• [ Pre-print ] Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
  Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura, Zhiding Yu, Chaowei Xiao, and Z. Morley Mao
  The first comprehensive dataset to benchmark corruption robustness of 3D point cloud, containing 75 corruption types!
  We win the best paper award in the SRML workshop co-located with ICLR'22!
  [Homepage]  [Code and Datasets]  [Benchmark] 

• [ ACM MM'23 ] VPA: Fully Test-Time Visual Prompt Adaptation
  Jiachen Sun, Mark Ibrahim, Melissa Hall, Ivan Evtimov, Z. Morley Mao, Cristian Canton Ferrer, and Caner Hazirbas
  Proceedings of the 31th ACM International Conference on Multimedia, Ottawa, Canada, Oct. 2023.
  

• [ ICML'23 ] A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification
  Jiachen Sun, Jiongxiao Wang, Weili Nie, Zhiding Yu, Z. Morley Mao, and Chaowei Xiao
  Proceedings of the 40th International Conference on Machine Learning, Hawaii, July, 2023.
  

• [ ECCV'22 ] Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
  Jiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, and Z. Morley Mao
  Proceedings of the 16th European Conference on Computer Vision, Tel-Aviv, Oct. 2022.
  [Datasets] 

• [ NeurIPS'21 ] Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions
  Jiachen Sun, Yulong Cao, Christopher Choy, Zhiding Yu, Anima Anandkumar, Z. Morley Mao, and Chaowei Xiao
  Proceedings of the 35th Conference on Neural Information Processing Systems, Online, Dec. 2021.
  [Paper]  [Supplements]  [Slides]
  

• [ BMVC'21 ] On Adversarial Robustness of 3D Point Cloud Classification under Adaptive Attacks
  Jiachen Sun, Karl Koenig, Yulong Cao, Qi Alfred Chen, and Z. Morley Mao
  Proceedings of the 32nd British Machine Vision Conference, Online, Nov. 2021.
  [ArXiv Version] 

• [ USENIX Security'20 ] Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures
  Jiachen Sun, Yulong Cao, Qi Alfred Chen, and Z. Morley Mao
  Proceedings of the 29th USENIX Security Symposium, Boston, USA, Aug. 2020.
  [ArXiv Version]  [BibTeX]  [Project Website]  [Talk Video]  [Slides]
  [Selected as UIUC CS598 Reading List]  [Selected as UT Dallas CS 6301.007 Reading List] 

• [ USENIX Security'24 ] On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasures
  Qingzhao Zhang, Shuowei Jin, Ruiyang Zhu, Jiachen Sun, Xumiao Zhang, Qi Alfred Chen, and Z. Morley Mao
  Proceedings of the 33rd USENIX Security Symposium, Philadelphia, USA, Aug. 2024.
  The first robustness analysis of multi-vehicle autonomous driving perception systems!
  

• [ CVPR'22 ] On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles
  Qingzhao Zhang, Shengtuo Hu, Jiachen Sun, Qi Alfred Chen, and Z. Morley Mao
  Proceedings of the 33rd IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, Nov. 2022.
  The first robustness analysis of the prediction module in autonomous driving systems!
  

• [ USENIX Security'21 ] Automated Discovery of Denial-of-Service Vulnerabilities in Connected Vehicle Protocols
  Shengtuo Hu, Qi Alfred Chen, Jiachen Sun, Yiheng Feng, Z. Morley Mao, and Henry Liu
  Proceedings of the 30th USENIX Security Symposium, Vancouver, Canada, Aug. 2021.
  

• [ MobiCom'21 ] EMP: Edge-assisted Multi-vehicle Perception
  Xumiao Zhang, Anlan Zhang, Jiachen Sun, Xiao Zhu, Yihua Ethan Guo, Feng Qian, and Z. Morley Mao
  Proceedings of the 27th ACM International Conference on Mobile Computing and Networking, 2021
  

• [ MobiSys'20 ] MPBond: Efficient Network-level Collaboration Among Personal Mobile Devices
  Xiao Zhu, Jiachen Sun, Xumiao Zhang, Yihua Ethan Guo, Feng Qian, and Z. Morley Mao
  Proceedings of the 18th ACM International Conference on Mobile Systems, Applications, and Services, Toronto, Canada, Jun. 2020.
  

• [ INFOCOM'19 ] Detecting Anomaly in Large-scale Network using Mobile Crowdsourcing
  Yang Li, Jiachen Sun, Wenguang Huang, and Xiaohua Tian
  Proceedings of IEEE International Conference on Computer Communications, Paris, France, May 2019.
  

• [ MobiCom'18 ] Ghostbuster: Detecting the Presence of Hidden Eavesdroppers
  Anadi Chaman, Jiaming Wang, Jiachen Sun, Haitham Hassanieh, and Romit Roy Choudhury
  Proceedings of the 24th ACM International Conference on Mobile Computing and Networking, New Delhi, India, Oct. 2018.
  [Selected as UT Austin CSE386 Reading List]  [Selected as UCSC CSE253 Reading List] 

• [ SRML@ICLR'22 ] ModelNet40-C: A Robustness Benchmark for 3D Point Cloud Recognition under Corruption
  Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura, Zhiding Yu, Chaowei Xiao, and Z. Morley Mao
  ICLR 2022 Workshop on Socially Responsible Machine Learning. April. 2022. (Best Paper Award)
  [PDF] 

• [ SRML@ICML'21 ] Improving Adversarial Robustness in 3D Point Cloud Classification via Self-Supervisions
  Jiachen Sun, Yulong Cao, Christopher Choy, Zhiding Yu, Chaowei Xiao, Anima Anandkumar, and Z. Morley Mao
  ICML 2021 Workshop on Socially Responsible Machine Learning. July. 2021.
  [PDF] [Poster]
  

• [ AdvMLCV@CVPR'20 ] Towards Robust LiDAR-based Perception in Autonomous Driving
  Jiachen Sun, Yulong Cao, Qi Alfred Chen, and Z. Morley Mao
  CVPR 2020 Workshop on Adversarial Machine Learning in Computer Vision, Seattle, USA, Jun. 2020. (Oral)
  [PDF] [DeepMind Travel Grant Award]

• [ UMAP Journal'17 ] Replacing the Kariba Dam
  Yiming Zhang, Jiachen Sun, Yisen Yao (Three authors contribute equally.)
  UMAP Journal of Undergraduate Mathematics and Its Applications. 2017. (Contest Paper of MCM).
  [Top 2 out of 2409 Participants] [Outstanding Winner & INFORMS Award]
  

 

Contact

 

jiachens AT umich DOT edu

 

Misc.

 

I love sports, and was a national second-class athlete. My records: 11.5 seconds for 100 meters race, and 1.7 meters for high jump. Besides Track and Field, I also love playing soccer, basketball, and volleyball. Mamba Forever! RIP Kobe Bean Bryant. I also love e-sports like League of Legends, PUBG, and CS:GO. I am a beginner of snowboarding and reallllly enjoy it this snow season!