Privacy/Security Risks in Machine/Federated Learning systems

Supervisory Team: Dr Han Wu

Project description:

In the wake of growing data privacy concerns and the enactment of the GDPR, Federated Learning (FL) has emerged as a leading privacy-preserving technology in Machine Learning. Despite its advancements, FL systems are not immune to privacy breaches due to the inherent memorisation capabilities of deep learning models. Such vulnerabilities expose FL systems to various privacy attacks, making the study of privacy in distributed settings increasingly complex and vital. This project aims to dive into the dynamics of attack methodologies (e.g., Membership Inference, Property Inference) and defensive mechanisms (e.g., Differential Privacy, Machine Unlearning) within FL environments, highlighting potential cross-disciplinary synergies. The outcomes will enhance the security, dependability and trustworthiness of AI applications.

The project will be conducted in collaboration with an interdisciplinary team, including academics from the University of Birmingham, Newcastle University, University of Cambridge, National University of Singapore, and industry experts.

Candidates may choose from, but are not limited to, the following research topics:

1. Machine Unlearning for AI applications based on tabular data.

  (Machine Unlearning is a novel privacy-preserving technology. Reference: https://dl.acm.org/doi/10.1145/3603620 )

2. Machine Unlearning for Federated Learning systems.

  (Reference: https://dl.acm.org/doi/10.5555/3618408.3618577 )

3. Privacy attacks in Machine/Federated Learning.

  (If you are more interested in conducting attacks rather than defences, refer

   to https://ieeexplore.ieee.org/document/10274102 )

4. Federated Learning for Smart Home applications.

  (Reference: https://ieeexplore.ieee.org/document/9415623 )

5. Adversarial attacks on Large Language Models.

  (Reference: https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/ )

Before you apply

Prospective candidates are invited to apply promptly as selections will be made on a rolling basis. Ideal candidates would have a strong background in Computer Sciences, Software Engineering, Artificial Intelligence, or related disciplines. Proficiency in Deep Learning and familiarity with tools such as PyTorch will be advantageous. Interested individuals are encouraged to reach out to the project supervisor, Dr Han Wu (h.wu@soton.ac.uk), for a detailed discussion prior to application.

About Dr Han Wu

Dr Han Wu is a Lecturer (Assistant Professor) in the School of Electronics & Computer Science at the University of Southampton. Before joining Southampton, he was a Postdoc at the University of Birmingham (2023-2024) and Newcastle University (2021-2023). More details can be found in his personal website: https://hanwu.ac.cn/

If you wish to discuss any details of the project informally, please contact Dr Han Wu, Cyber Security Research group, Email: h.wu@soton.ac.uk

Entry Requirements

A good undergraduate degree (at least a UK 2:1 honours degree, or its international equivalent).

Closing date: 31 August 2025. Applications will be considered in the order that they are received, the position will be considered filled when a suitable candidate has been identified.

Funding: We offer a range of funding opportunities for both UK and international students, including Bursaries and Scholarships. For more information please visit PhD Scholarships Doctoral College University of Southampton Funding will be awarded on a rolling basis, so apply early for the best opportunity to be considered.

How To Apply

Apply online: Search for a Postgraduate Programme of Study (soton.ac.uk) Select programme type (Research), 2025/26, Faculty of Engineering and Physical Sciences, next page select “PhD Computer Science (Full time)”. In Section 2 of the application form you should insert the name of the supervisor Dr Han Wu

Applications should include:

Research Proposal

Curriculum Vitae

Two reference letters

Degree Transcripts/Certificates to date

Contact email: feps-pgr-apply@soton.ac.uk