Associate Professor
Department of Electrical and Electronic Engineering
The Hong Kong Polytechnic University
Email: [email protected]
Research Interests
- Differential privacy
- Adversarial machine learning
About Me
I am an associate professor in the department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University. I received my PhD degree from Renmin University of China in 2020. My research interests include data privacy and security, and adversarial machine learning. You can refer to our research lab ASTAPLE for more information.
I have openings for 2-4 PhD students (Fall 2026 Admission), Research Assistants, and Postdoctoral Fellows in the field of differential privacy, and adversarial machine learning. If you are interested, please send me your CV at [email protected].
News
- Jul. 2026: Our paper “PrivFDM: Differentially Private Federated Diffusion Models for Image Synthesis” is accepted by ACM International Conference on Multimedia (MM 2026).
- Jun. 2026: A research project entitled “Unlocking Relations in Noise: Relational Knowledge Mining with Local Differential Privacy” is awarded by Research Grant Council with HK$ 975,916 (2027.01-2029.12).
- May 2026: Our three papers “Differentially Private Cross-Silo Recommendation from Implicit Feedback”, “Unlearning Isn’t Deletion: Investigating Reversibility of Machine Unlearning in LLMs”, and “On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression”, are accepted by International Conference on Machine Learning (ICML 2026).
- Apr. 2026: Our paper “Hitchhiking on Inherent Randomness: Diffusion-based Graph Generation under Differential Privacy” is accepted by ACM Conference on Computer and Communications Security (CCS 2026).
- Apr. 2026: Our paper “From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning” is accepted by Annual Meeting of the Association for Computational Linguistics (ACL 2026).
- Apr. 2026: Our paper “mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA” is accepted by International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026).
- Mar. 2026: Our paper “Sparse Estimation Under Local Differential Privacy at All Privacy Levels” is accepted by IEEE Symposium on Security and Privacy (S&P 2026).