Our papers “MER-Inspector: Assessing Model Extraction Risks from An Attack-Agnostic Perspective” and “FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning” are accepted by ACM TheWebConf 2025 (WWW 2025).
Our papers “A Sample-Level Evaluation and Generative Framework for Model Inversion Attacks” and “Exploring Intrinsic Alignments within Text Corpus” are accepted by Annual AAAI Conference on Artificial Intelligence (AAAI 2025).
Our papers “Structure-Preference Enabled Graph Embedding Generation under Differential Privacy” and “Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs” are accepted by IEEE International Conference on Data Engineering (ICDE), 2025.
Our paper “PrivDPR: Synthetic Graph Publishing with Deep PageRank under Differential Privacy” is accepted by SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025).
Our paper “Federated Heavy Hitter Analytics with Local Differential Privacy” is accepted by International Conference of Management of Data (SIGMOD 2025)”. Our paper “Membership Inference Attacks and Defenses in Federated Learning: A Survey” is accepted by ACM Computing Surveys.
It’s my honor to announce the establishment of PolyU Research Centre for Privacy and Security Technologies in Future Smart Systems (RCPST) in September 2024. The aim of this center is to bridge between academic security and privacy research and real-life security and legal needs from smart system industries. For information, news, and events of this…
I have been awarded an ITF grant with project title “MyGPTShield: A Personalized Privacy-Preserving Prompt Service for Large Generative AI Models”. The total amount is HK$2,000,010.
I have openings for 3+ PhD students (2025 in-take), and 4+ research assistants/postdoc researchers (immediately available) in the field of machine learning, data security and privacy. The detailed requirements of PhD applicants are as follows: Bachelor or Master degree in Computer Science, Software Engineering or Information Engineering in well-known universities. Preferences are given to applicants…
A research project entitled “Right To Be Forgotten Made Easy: Machine Unlearning, Differential Privacy and Beyond” has been awarded by Research Grant Council, HKSAR with HK$1,038,967 (2025-2027).
Our paper “PriPL-Tree: Accurate Range Query for Arbitrary Distribution under Local Differential Privacy” has been accepted by International Conference on Very Large Databases (VLDB 2024).