Publisher
source

University of Surrey

Just Landed

PhD Studentship in Federated Machine Unlearning for Privacy-Preserving AI University of Surrey in United Kingdom

Degree Level

PhD

Field of study

Computer Science

Funding

Fully funded studentship covering home university fees, additional research training, travel funds, and UKRI standard rate stipend (£21,805 for 2026/27 academic year). Funding lasts 3.5 years.

Deadline

Oct 31, 2026

Country flag

Country

United Kingdom

University

University of Surrey

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

Apply for this position

Keywords

Computer Science
Information Technology
Mathematics
Data Privacy
Federated Learning
Statistics
Distributed System
ML

Suggested positions

About this position

PhD studentship at the University of Surrey in Computer Science on robust, certified, and scalable federated machine unlearning for privacy-preserving AI. The project sits at the intersection of federated learning, machine learning, differential privacy, adversarial robustness, distributed systems, and trustworthy AI.

The research aims to develop next-generation federated machine unlearning methods that can efficiently remove the influence of specific data from trained models while preserving utility and participant privacy. Topics highlighted in the advert include certified unlearning with formal guarantees, robustness to adversarial relearning, evaluation and verification tools, scalable unlearning for foundation models, and unlearning as an AI safety primitive.

This is a fully funded PhD studentship for UK/home fee candidates. Funding covers home university fees, additional research training, travel funds, and a UKRI standard-rate stipend of £21,805 for 2026/27. Funding is available for 3.5 years.

Eligibility highlights include a first-class or strong upper-second-class undergraduate degree, or a Master's degree, in Computer Science, Mathematics, Statistics, or a closely related field; solid grounding in machine learning and/or probability/statistics; Python programming; familiarity with PyTorch, JAX, or similar frameworks; strong analytical skills; and good English communication. Experience in federated learning, differential privacy, adversarial robustness, distributed systems, or LLM fine-tuning is desirable.

Supervisors: Dr Pedro Porto Buarque de Gusmao and Dr Frank Guerin. Start date is January 2027, with later start dates possible by contacting Dr Gusmao after the deadline. Deadline: 31 October 2026.

Funding details

Fully funded studentship covering home university fees, additional research training, travel funds, and UKRI standard rate stipend (£21,805 for 2026/27 academic year). Funding lasts 3.5 years.

What's required

Open to candidates who pay UK/home rate fees. Applicants must meet the minimum entry requirements for the PhD programme. Preferred background includes a first-class or strong upper-second-class undergraduate degree, or a Master's degree, in Computer Science, Mathematics, Statistics, or a closely related field. Candidates should have solid grounding in machine learning and/or probability/statistics, programming proficiency in Python, familiarity with ML frameworks such as PyTorch or JAX, strong analytical and problem-solving skills, and good written and verbal English. Experience in federated learning, differential privacy, adversarial robustness, distributed systems, or LLM fine-tuning is desirable but not required.

How to apply

Apply through the Computer Science PhD programme page. Instead of a research proposal, upload a document stating the project title and the relevant supervisor's name. Contact Dr Pedro Porto Buarque de Gusmao after the deadline passes if you need to discuss a later start date.

More information can be found here

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?