southampton

Research interests

Federated Learning

Adversarial Machine Learning

Data Privacy

Accepting applications from PhD students.

About

Dr Han Wu is a Lecturer (Assistant Professor) in the School of Electronics & Computer Science (ECS) at the University of Southampton. His position is anchored within the Cyber Security group. Currently, he is deeply engaged in addressing research challenges in the realm of Dependable and Secure Machine Learning Technology. More details can be found in his homepage.

His research interests are broad and encompass a variety of key areas, including Federated Learning, Inference Attacks, Differential Privacy, Tabular Data Synthesis, and Machine Unlearning. His work aims to contribute to the advancement of secure and reliable machine learning systems that can be trusted in sensitive and critical applications.

Prior to joining the University of Southampton, Dr Han Wu was a Research Fellow (2023-2024) in the School of Computer Science at the University of Birmingham. In this role, Han worked with Prof. Aad van Moorsel on the EPSRC-funded AGENCY (£ 2.7M) project. Han also worked as a Research Associate (2021-2023) for the EPSRC-funded FinTrust (£ 1.0M) project at Newcastle University.

Dr Han Wu obtained PhD degree in Computer Science from the Free University of Berlin in 2020. His PhD supervisor is Prof. Katinka Wolter. He received his Bachelor’s degree from Huazhong University of Science and Technology (HUST) in 2013, and his Master’s degree from Tongji University in 2016.

Research

Research groups

Member of:

Cyber Security

Research interests

Federated Learning
Adversarial Machine Learning
Data Privacy
Distributed Data Synthesis
Machine Unlearning

Current research

My research interests encompass three major domains, each presenting a wide range of advanced possibilities. In the realm of Dependable and Secure Machine Learning, I explore pivotal concepts including Federated Learning, Inference Attacks, Differential Privacy, and the interesting frontier of Machine Unlearning. Additionally, my expertise extends to Distributed Data Synthesis, involving the development of Tabular Data Synthesis Models, the nuanced practice of Distributed Learning using Tabular GANs, and the rigorous evaluation of Synthetic Data. Beyond these pursuits, I'm strongly dedicated to propelling application-oriented and Interdisciplinary Research initiatives associated with privacy and security in AI applications. This dedication is rooted in my extensive involvement in collaborative projects that bring together experts from diverse backgrounds, fostering a comprehensive approach to intricate challenges.

My research agenda encompasses, but is not restricted to, the following areas:

Machine Unlearning for AI applications based on tabular data.
Machine Unlearning for Federated Learning systems.
Privacy attacks in Machine/Federated Learning.
Federated Learning for Smart Home applications.
Adversarial attacks against Large Language Models.