Author: haibo

Our paper “DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release” has been accepted by PVLDB 2024. Our papers “LDPRecover: Recovering Frequencies from Poisoning Attacks against Local Differential Privacy” and “FRESH: Towards Efficient Graph Queries in an Outsourced Graph” have been accepted by IEEE International Conference on Data Engineering (ICDE ’24), Utrecht, Netherlands, May 2024.

Prof. Hu start to serve as an associate editor on the editorial board of IEEE Transactions on Knowledge and Data Engineering (TKDE) and IEEE Transactions on Information Forensics and Security (TIFS).

Our paper “TED+Utility-Aware Time Series Data Release with Anomalies under TLDP” has been accepted by IEEE Transactions on Mobile Computing (TMC). Our paper “A Utility-aware Anonymization Model for Multiple Sensitive Attributes Based on Association Concealment” has been accepted by IEEE Transactions on Dependable and Secure Computing (TDSC). Our paper “DeepMark: A Scalable and Robust Framework for DeepFake Video Detection” has been accepted by ACM Transactions […]

Our paper “TED+: Towards Discovering Top-k Edge-Diversified Patterns in a Graph Database” has been accepted by IEEE TKDE. Our paper “Secure Traffic Monitoring with Spatio-temporal Metadata Protection Using Oblivious RAM” has been accepted by IEEE Transactions on Intelligent Transportation Systems. Our paper ““Collecting Multi-type and Correlation-Constrained Streaming Sensor Data with Local Differential Privacy” has been accepted by ACM Transactions on Sensor Networks (TOSN).

Dr. Ye has been awarded a 面上项目 with title “本地化差分隐私攻防之数据重构攻击研究” from NSFC with CNY 500,000 (2024.01-2027.12).

Prof. Hu has been awarded a RGC/GRF grant with project title “Local Tweaks for Privacy-Preserving Training in Machine Learning at Scale”. The total amount is HK$1,228,619. Dr. Ye has been awarded a RGC/GRF grant with project title “Small Leaks Sink Great Ships: Data Recovery Attacks and Defense in Local Differential Privacy”. The total amount is HK$1,096,927.

Our paper “Collaborative Sampling for Partial Multi-dimensional Value Collection under Local Differential Privacy” has been accepted by IEEE TIFS. Our paper “PUTS: Privacy-Preserving and Utility-Enhancing Framework for Trajectory Synthesization” has been accepted by IEEE TKDE.

Our paper “Trajectory Data Collection with Local Differential Privacy” has been accepted by VLDB 2023.

Our paper “3DFed: Adaptive and Extensible Framework for Covert Backdoor Attack in Federated Learning” has been accepted by IEEE S&P 2023.

Our paper “Differential Aggregation against General Colluding Attackers” has been accepted by IEEE ICDE 2023.