My research interests include data privacy and security, and adversarial machine learning. As a practitioner in this field, I am interested in finding and solving real problems in a pragmatic manner. The following are some research fields that I am currently working on.

• Differential Privacy

  With the prevalence of big data analytics, service providers become increasingly enthusiastic in collecting and analyzing usage data to improve their services. However, the collection of user data comes at the price of privacy risks, not only for users but also for service providers who are vulnerable to internal and external data breaches. As an answer to privacy-preserving data collection and analysis, Differential Privacy (DP), either in its centralized or local setting, has become a de facto standard for individual privacy protection.

• Adversarial Machine Learning

  With the prevalence of Big Data and AI, machine learning models are trained and deployed to facilitate humans in daily life. However, in many hostile environments, the training and deployment of these models can be undermined and their integrity can be severely jeopardized. Adversarial machine learning studies such security issues and aims for the confidentiality, integrity, availability, and accountability of machine learning techniques under malicious and stressful settings.

Advisees

• PhD Students

  Xun Ran	since 01/2023
  Yuemin Zhang	since 09/2023
  Liantong Yu	since 01/2024
  Shiyu Zhang	since 01/2024
  Renxuan Hou	since 09/2024
  Di Wu	since 09/2024
  Zitong Li	since 09/2024
  Xinyue Li	since 09/2024

• Research Assistants

  Wenbo Yu	since 08/2024
  Yu Shi	since 08/2024

Research Grants

• Harnessing Sensitive Statistics from the Crowd: Towards Scalable Private Federated Analytics
  PI: RGC/Early Career Scheme (ECS), 25207224, 2025.01-2027.12, HKD 992,994. (Early Career Award)

• 面向大模型微调的差分隐私数据保护技术研究
  PI: Open Research Fund of The State Key Laboratory of Blockchain and Data Security, 2024.08-2026.07, CNY 100,000

• Federated Graph Management and Querying: Subgraphs, Keywords, and Privacy
  Co-PI: RGC/Young Collaborative Research Grant (YCRG), C2003-23Y, 2024.06-2027.05, HKD 4,854,870

• Small Leaks Sink Great Ships: Data Recovery Attacks and Defense in Local Differential Privacy
  PI: RGC/General Research Fund (GRF), 15208923, 2024.01-2026.12, HKD 1,096,927

• Towards Provable On-Device Data Privacy for Complex Analytics and Its Applications
  PI: Industrial Research Grant, 2024.01-2024.12, HKD 495,000

• 本地化差分隐私攻防之数据重构攻击研究
  PI: NSFC (面上项目), 62372122, 2024.01-2027.12, CNY 500,000

• Efficient OLAP Operations under Local Differential Privacy
  PI: PolyU Research Grant, 2023.05-2026.04, HKD 500,000

• Byzantine-Robust Data Collection under Local Differential Privacy Model
  PI: RGC/General Research Fund (GRF), 15225921, 2022.01-2024.12, HKD 838,393

• 恶意敌手模型下的本地化差分隐私技术探索
  PI: NSFC (青年科学基金项目), 62102334, 2022.01-2024.12, CNY 300,000

• Privacy-Preserving Data Analytics under Byzantine Attack
  PI: PolyU Research Grant, 2021.03-2023.06, HKD 250,000

• Medical Data Mining based on Belief Rule Base
  PI: National Collegiate Innovation and Entrepreneurship Training Program, 201410386009, 2014.07-2015.06, CNY 20,000