Differential Privacy

Differential privacy is the de facto standard privacy notion for privacy-preserving data analysis and publishing. Roughly speaking, differential privacy means the output distributions from an analysis will be essentially the same, regardless whether any individual joins, or refrains from joining, the dataset. This is usually achieved by adding a pre-determined amount of randomness, or “noise”, into a computation performed on a dataset. The noise makes the output insensitive to any single record in the dataset, so that every individual in the dataset can plausibly deny that their data was included.

My research on differential privacy focuses on developing novel mechanisms with differential privacy guarantee, while striking a balance among privacy, utility and efficiency.

Related publications

  1. USENIX
    Addressing Sensitivity Distinction in Local Differential Privacy: A General Utility-Optimized Framework
    Xingyu He, Youwen Zhu, Rongke Liu, Gaoning Pan, and Changyu Dong
    In 34th USENIX Security Symposium , 2025
    PDF
  2. TIFS
    Side-channel Attacks and New Principles in the Shuffle Model of Differential Privacy
    Shaowei Wang, Jin Li,  Changyu Dong, Jin Li, Zhili Zhou, Di Wang, and Zikai Wen
    IEEE Trans. Inf. Forensics Secur., 2025
    PDF
  3. USENIX
    Beyond Statistical Estimation: Differentially Private Individual Computation via Shuffling
    Shaowei Wang,  Changyu Dong, Xiangfu Song, Jin Li, Zhili Zhou, Di Wang, and Han Wu
    In 34th USENIX Security Symposium , 2025
    HTML PDF
  4. Inf. Sci.
    DPGazeSynth: enhancing eye-tracking virtual reality privacy with differentially private data synthesis
    Xiaojun Ren, Jiluan Fan, Ning Xu, Shaowei Wang,  Changyu Dong, and Zikai Wen
    Information Sciences, 2024
    HTML PDF
  5. TIFS
    ABSyn: An Accurate Differentially Private Data Synthesis Scheme With Adaptive Selection and Batch Processes
    Jingyu Jia, Xinhao Li, Tong Li, Zhewei Liu, Chang Tan, Siyi Lv, Liang Guo,  Changyu Dong, and Zheli Liu
    IEEE Trans. Inf. Forensics Secur., 2024
    HTML PDF
  6. TIFS
    Distributed Differential Privacy via Shuffling Versus Aggregation: A Curious Study
    Yu Wei, Jingyu Jia, Yuduo Wu, Changhui Hu,  Changyu Dong, Zheli Liu, Xiaofeng Chen, Yun Peng, and Shaowei Wang
    IEEE Trans. Inf. Forensics Secur., 2024
    HTML PDF
  7. Inf. Sci.
    The influence of explanation designs on user understanding differential privacy and making data-sharing decision
    Zikai Alex Wen, Jingyu Jia, Hongyang Yan, Yaxing Yao, Zheli Liu, and Changyu Dong
    Information Sciences, 2023
    HTML PDF
  8. Inf. Sci.
    Total variation distance privacy: Accurately measuring inference attacks and improving utility
    Jingyu Jia, Chang Tan, Zhewei Liu, Xinhao Li, Zheli Liu, Siyi Lv, and Changyu Dong
    Information Sciences, 2023
    HTML PDF
  9. IJIS
    Understanding adaptive gradient clipping in DP-SGD, empirically
    Guanbiao Lin, Hongyang Yan, Guang Kou, Teng Huang, Shiyu Peng, Yingying Zhang, and Changyu Dong
    Int. J. Intell. Syst., 2022
    PDF
  10. SOUPS
    New Differential Privacy Communication Pipeline and Design Framework (Poster)
    Jingyu Jia, Zikai Wen, Zheli Liu, and Changyu Dong
    In 18th Symposium on Usable Privacy and Security, 2022
    PDF
  11. TPDS
    Differentially Private Byzantine-robust Federated Learning
    Xu Ma, Xiaoqian Sun, Yuduo Wu, Zheli Liu, Xiaofeng Chen, and Changyu Dong
    IEEE Trans. Parallel Distributed Syst., 2022
    HTML PDF
  12. ICDM
    Differentially Private String Sanitization for Frequency-Based Mining Tasks
    Huiping Chen,  Changyu Dong, Liyue Fan, Grigorios Loukides, Solon P. Pissis, and Leen Stougie
    In IEEE International Conference on Data Mining, 2021
    HTML
  13. USENIX
    How to Make Private Distributed Cardinality Estimation Practical, and Get Differential Privacy for Free
    Changhui Hu, Jin Li, Zheli Liu, Xiaojie Guo, Yu Wei, Xuan Guang, Grigorios Loukides, and Changyu Dong
    In 30th USENIX Security Symposium, 2021
    HTML PDF