Xiaochen Zhu (he/him)

PhD Student,
Computer Science and Artificial Intelligence Laboratory,
Department of Electricial Engineering and Computer Science,
Massachusetts Institute of Technology

Address: Room 32-G890, 32 Vassar St, Cambridge, MA 02139
Email: xczhu@mit.edu

My name can be pronounced approximately as Shee-aw Chen Joo

Links to: CV, Google Scholar, DBLP, GitHub, Twitter

Jump to section: [About] [Publications] [Teaching] [Service] [Honors]

About me

I'm a PhD student in the EECS department at MIT who started in fall 2024, and I am very fortunate to be advised by Prof Srini Devadas.

Prior to this, I graduated with bachelor's degrees in computer science and mathematics from National University of Singapore (NUS) in 2023, where I was very fortunate to be advised by Prof Xiaokui Xiao and Prof Vincent Tan. Upon graduation, I continued my research at NUS as a research assistant with the same advisors until July 2024.

I am passionate about data privacy. Currently, my research interests are in differential privacy, federated learning and ML privacy. I aim to identify privacy vulnerabilities in various algorithms and design privacy-preserving protocols to enhance their privacy. I try to tackle these problems via both theoretical and empirical lenses. Please refer to the Publications section for more details.

Publications

  1. Passive Inference Attacks on Split Learning via Adversarial Regularization
    Xiaochen Zhu, Xinjian Luo, Yuncheng Wu, Yangfan Jiang, Xiaokui Xiao, Beng Chin Ooi
    Proceedings of the 32nd Annual Network and Distributed System Security Symposium (NDSS), to appear, Feb 2025
  2. On Data Distribution Leakage in Cross-Silo Federated Learning
    Yangfan Jiang, Xinjian Luo, Yuncheng Wu, Xiaochen Zhu, Xiaokui Xiao, Beng Chin Ooi
    IEEE Transcations on Knowledge and Data Engineering (TKDE), 36(7): 3312-3328, 2024
  3. Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation
    Xiaochen Zhu, Vincent Y. F. Tan, Xiaokui Xiao
    Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS), 2651-2664, Nov 2023 (AR=234/1222≈19.15%)
  4. Link Local Differential Privacy in GNNs via Bayesian Estimation
    Xiaochen Zhu
    Companion of the 2023 International Conference on Management of Data (SIGMOD), 265-267, Jun 2023
    First place in SIGMOD Student Research Competition (Undergraduate Category)

Teaching (details)

I have taught the following courses as a teaching assistant at NUS. Mostly, I taught weekly tutorials/labs and/or marked assignments.

Service

I've served as a reviewer for ACL ARR (2024) and IEEE TSC. I've also served on the Artifact Evaluation Committee (AEC) for ACM CCS (2023, 2024).

Selected awards