Scholar

Han Wu

Google Scholar ID: V3rj4hQAAAAJ

Assistant Professor (Lecturer) in Cyber Security, School of ECS, University of Southampton

Data PrivacyPrivacy-preserving machine learningDependability

Citations & Impact

All-time

Citations

395

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

1 items

2026

Cited

Resume (English only)

Academic Achievements

Publications:
- Paper on Vertical Federated Learning accepted by DSN 2025.
- Paper about personalisation in Shuffle Differential Privacy accepted by USENIX Security 2025.
- GAN-based social media bots paper accepted by IEEE Transactions on Computational Social Systems journal.
- Scoping review paper about online harms in smart homes accepted by Future Generation Computer Systems journal.
- Paper on Federated Learning attack accepted by ISSRE 2022.
Awards:
- Post-Doctoral Enrichment Award 2022 granted by the Alan Turing Institute.
- ECS Pump Priming Fund amounting to £1,730.
- UnFed: Selective Forgetting in Federated Financial Applications project received £20,000 grant from EPSRC Network Plus.

Research Experience

From April 2024, an Assistant Professor (Lecturer) in the School of Electronics & Computer Science (ECS) at the University of Southampton, part of the Cyber Security group. Prior to joining SOTON, a Research Fellow (2023-2024) in the School of Computer Science at the University of Birmingham, working with Prof. Aad van Moorsel on the EPSRC-funded AGENCY (£2.7M) project. Also worked as a Research Associate (2021-2023) for the EPSRC-funded FinTrust (£1.0M) project at Newcastle University.

Education

PhD in Computer Science from the Free University of Berlin in 2020, supervised by Prof. Katinka Wolter; Master's degree from Tongji University in 2016; Bachelor's degree from Huazhong University of Science and Technology (HUST) in 2013.

Background

Research interests include Federated Learning, Inference Attacks, Differential Privacy, Tabular Data Synthesis, and Machine Unlearning. Aiming to advance secure and reliable machine learning systems for sensitive applications.

Miscellany