Haochen Sun
News
Education
Publications
Contact
Quick Links

Haochen Sun

I am a PhD candidate in the Data Systems Group at the Cheriton School of Computer Science, University of Waterloo, advised by Prof. Xi He. My research focuses on enhancing the security and privacy of machine learning and data management systems using differential privacy (DP) and cryptography. I am actively seeking a research internship in areas related to differential privacy, including secure computations for DP and DP foundation models.

News

  • (October 2025) VDDP is now open-sourced, with code and raw experimental logs available. Please help us reproduce and submit your reproduction report!
  • (September 2025) I passed the Comprehensive II exam.
  • (August 2025) I am honoured to have received the David R. Cheriton Graduate Scholarship!

Education

  • PhD in Computer Science, University of Waterloo, 2022 - Present
  • BSc in Data Science & Technology and Computer Science, The Hong Kong University of Science and Technology, 2018 - 2022

Publications

Blue denotes my current PhD thesis work (since May 2024), with more publications forthcoming. Grey denotes publications from previous projects that I am no longer involved with. An asterisk (*) indicates co-first authorship.

  1. Haochen Sun and Xi He. "GPM: The Gaussian Pancake Mechanism for Planting Undetectable Backdoors in Differential Privacy." Preprint, 2025. [arXiv, GitHub]
  2. Haochen Sun and Xi He. "VDDP: Verifiable Distributed Differential Privacy under the Client-Server-Verifier Setup." Preprint, 2025. [arXiv, GitHub]
  3. Haochen Sun*, Shufan Zhang*, Karl Knopf*, Shubhankar Mohapatra, Wei Pang, Calvin Wang, Yingke Wang, Masoumeh Shafieinejad, David Emerson, and Xi He. "FedDPSyn: Federated Tabular Data Synthesis with Computational Differential Privacy." Theory and Practice of Differential Privacy (TPDP), 2025.
  4. Haochen Sun, Jason Li, and Hongyang Zhang. "zkLLM: Zero-Knowledge Proofs for Large Language Models." Proceedings of the ACM Conference on Computer and Communications Security (CCS), 2024.
  5. Haochen Sun, Tonghe Bai, Jason Li, and Hongyang Zhang. "zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training." IEEE Transactions on Information Forensics and Security (TIFS), 2025.
  6. Haochen Sun, Jimmy C. H. Fung, Yiang Chen, Zhenning Li, Dehao Yuan, Wanying Chen, and Xingcheng Lu. "Development of an LSTM broadcasting deep-learning framework for regional air pollution forecast improvement." Geoscientific Model Development, 2022.
  7. Haochen Sun, Jimmy C. H. Fung, Yiang Chen, Wanying Chen, Zhenning Li, Yeqi Huang, Changqing Lin, Mingyun Hu, and Xingcheng Lu. "Improvement of PM2.5 and O3 forecasting by integration of 3D numerical simulation with deep learning techniques." Sustainable Cities and Society, 2021.

Contact

  • Email: I typically respond within 12 hours. To ensure your message reaches me, please use your institutional email address. Messages from personal accounts like Gmail or 163.com, or emails written in non-English or overly brief/informal styles, may be mistakenly filtered as spam.
  • SIP: For Zoom, Teams, and similar platforms.
  • Office: DC 3553, University of Waterloo, 200 University Avenue West, Waterloo, Ontario, N2L 3G1, Canada.
  • WeChat, Telegram, etc. are not used for professional communication. This is in accordance with university policy and guidelines, and is also due to previous negative and unacceptable incidents.

Quick Links

  • CV
  • LinkedIn
  • DBLP
  • Google Scholar
  • GitHub
  • ORCID