Collaborative Research: IMR: MM-1B: Foundations for Differentially Private Internet Measurement

Summary

Internet measurement research has been providing critical insights and evidence support in guiding the design of Internet infrastructures. However, how to share and use Internet measurement data while respecting users' privacy is still challenging. To protect privacy, most works choose to anonymize sensitive fields or only publish the aggregated statistics, but such methods are vulnerable to privacy attacks. Differential privacy, which provides guaranteed privacy protection for data release, has gained prominent traction from companies and government agencies, and is a natural choice for sharing Internet measurement data. However, a critical gap remains to identify how differential privacy can be applied to networking problems. This project aims to understand privacy issues and then lay the foundations for deploying differential privacy in the processing pipeline of Internet measurement data. The project's broader significance and importance include transferring the technologies to industry, involving members from under-represented groups, and disseminating outcomes through K-12 outreach and community services.

Support

People

  • Tianhao Wang. PI on this project (uVa CS).
  • Zhou Li. PI on this project (UCI EECS).
  • Joann Qiongna Chen. Ph.D. Student Researcher (UCI EECS).
  • Danyu Sun. Ph.D. Student Researcher (UCI EECS).

Publications

  • [ACSAC'23b] Mingtian Tan, Xiaofei Xie, Jun Sun, and Tianhao Wang. "Mitigating Membership Inference Attacks via Weighted Smoothing." In Proceedings of the 2023 Annual Computer Security Applications Conference. 2023.
  • [ACSAC’23a] Joann Qiongna Chen, Tianhao Wang, Zhikun Zhang, Yang Zhang, Somesh Jha and Zhou Li. "Differentially Private Resource Allocation." The 39th Annual Computer Security Applications Conference, 2023.
  • [TPDP'23] Joann Qiongna Chen, Tianhao Wang, Zhikun Zhang, Yang Zhang, Somesh Jha and Zhou Li. "Differentially Private Resource Allocation." Theory and Practice of Differential Privacy, 2023.​
  • [USENIX Security'23] Haiming Wang, Zhikun Zhang, Tianhao Wang, Shibo He, Michael Backes, Jiming Chen, and Yang Zhang. "PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Model." In USENIX Security Symposium 2023.
  • [PACMMOD'23] Zihang Xiang, Tianhao Wang, Wanyu Lin, and Di Wang. "Practical Differentially Private and Byzantine-resilient Federated Learning." Proceedings of the ACM on Management of Data 1, no. 2 (2023): 1-26.
  • [PVLDB'23] Zitao Li, Tianhao Wang, and Ninghui Li. "Differentially Private Vertical Federated Clustering." Proceedings of the VLDB Endowment 16, no. 6 (2023): 1277-1290.
  • [CCS'23] Minxin Du, Xiang Yue, Sherman Chow, Tianhao Wang, Chenyu Huang, and Huan Sun. "DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass." In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. 2023.
  • [CCS'22] Samuel Maddock, Graham Cormode, Tianhao Wang, Carsten Maple, and Somesh Jha. "Federated boosted decision trees with differential privacy." In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pp. 2249-2263. 2022.

    • Software and Datasets

  • Code and dataset for [ACSAC'23a]
  • Code and dataset for [ACSAC'23b]

    • Outreach

  • To be updated