Chulin Xie



Hi! I am a third-year Ph.D. student in Computer Science at University of Illinois at Urbana-Champaign, advised by Prof. Bo Li.

My research focuses on enhancing the security/privacy/generalization of ML, and the intersection of these topics, especially in federated learning and language models. Previously, I received my Bachelor degree from Computer Science department at Zhejiang University in July 2020. I was a research intern at Microsoft Research and NVIDIA Research.


Sep 21, 2023 Our work on GPT model trustworthiness, DecodingTrust, is accepted to NeurIPS 2023 as Oral.
Sep 2, 2023 Our work on differential privacy and certified robustness in FL is accepted to ACM CCS 2023!
May 22, 2023 I start a research internship at Microsoft Research Redmond, working on privacy of LLMs.
May 12, 2023 Glad to receive ICML 2023 Travel Award.
Oct 17, 2022 Glad to receive SatML 2022 Travel Award.
Sep 14, 2022 Our paper CoPur for robust collaborative inference is accepted to NeurIPS 2022!

Selected Research

  1. Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
    Chulin Xie, Yunhui Long, Pin-Yu Chen, Qinbin Li, Sanmi Koyejo, and Bo Li
    In ACM Conference on Computer and Communications Security (CCS), 2023
  2. DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
    Boxin Wang*, Weixin Chen*, Hengzhi Pei*, Chulin Xie*, Mintong Kang*, Chenhui Zhang*, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, and Bo Li
    In Conference on Neural Information Processing Systems (NeurIPS), 2023 (Oral)
  3. PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees
    Chulin Xie, De-An Huang, Wenda Chu, Daguang Xu, Chaowei Xiao, Bo Li, and Anima Anandkumar
    In preprint, 2023
  4. CoPur: Certifiably Robust Collaborative Inference via Feature Purification
    Jing Liu, Chulin Xie, Sanmi Koyejo, and Bo Li
    In Conference on Neural Information Processing Systems (NeurIPS), 2022
  5. Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM
    Chulin Xie, Pin-Yu Chen, Ce Zhang, and Bo Li
    In Federated Learning Workshop at NeurIPS, 2022
  6. Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
    Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, and Tom Goldstein
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
  7. CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
    Chulin Xie, Minghao Chen, Pin-Yu Chen, and Bo Li
    In International Conference on Machine Learning (ICML), 2021
  8. Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
    Chulin Xie*, Chuxin Wang*, Bo Zhang, Hao Yang, Dong Chen, and Fang Wen
    In Conference on Computer Vision and Pattern Recognition (CVPR), 2021
  9. DBA: Distributed Backdoor Attacks against Federated Learning
    Chulin Xie, Keli Huang, Pin-Yu Chen, and Bo Li
    In International Conference on Learning Representations (ICLR), 2020


Teaching Assistant

  • CS 446: Machine Learning, Fall 2023