About this position
Unmanned Aerial Vehicle (UAV) swarms are becoming increasingly important for defence, emergency response, infrastructure inspection, and future autonomous systems. These swarms can use federated learning (FL), where multiple UAVs collaboratively train artificial intelligence models without sharing raw mission data. This supports privacy and efficiency, but it also creates a serious security risk: a compromised UAV may send poisoned model updates that corrupt the shared intelligence of the swarm.
This PhD will develop lightweight, trust-aware methods to make FL models safer for UAV swarms. The successful candidate will design algorithms that identify suspicious model updates, reduce the influence of compromised UAVs, and preserve useful learning from honest UAVs operating with different data and unreliable communications.
The project includes training in AI, cyber security, FL, privacy-preserving computation, edge intelligence, and UAV simulation.
Objectives
- Define a UAV-PFL threat model covering poisoning, backdoor attacks, non-IID data, and intermittent communication.
- Build a reproducible UAV-PFL benchmark for evaluating state-of-the-art secure and robust aggregation methods.
- Design multi-evidence trust metrics using update behaviour, validation impact, temporal consistency, and communication reliability.
- Develop a privacy-aware trust-calibrated aggregation algorithm to down-weight suspicious updates.
- Evaluate accuracy, attack resilience, privacy leakage, communication overhead, computation cost, and deployment feasibility.
Funding
These are doctoral teaching assistant positions that combine a PhD programme with a university teaching contract. Your time will be split approximately 60% on research and 40% on teaching. This provides excellent preparation for candidates considering an academic career at a university.
The teaching component will typically run over the 22 teaching weeks per year and the 4 assessment weeks. You will help deliver an outstanding student experience by supporting lead academics with classroom and lab teaching and assessment, further building the skills developed within your PhD research programme.
The position is grade 6 with a current salary of £31,236 and includes payment of home PhD tuition fees for the duration of the 6-year award. Home students can apply. Applicants must have the right to work in the UK. We are unable to offer visa sponsorship for this role.
Candidate requirements
Applicants should hold, or expect to obtain, an undergraduate and preferably a postgraduate qualification in computer science, artificial intelligence, cyber security, data science, or a closely related discipline.
Essential
- Good programming skills, preferably in Python/C#.
- Experience with machine learning, deep learning, or experimental AI evaluation.
- Interest in secure distributed AI, federated learning, adversarial machine learning, UAV systems, or edge intelligence.
- Strong analytical, problem-solving, and independent research skills.
- Good written communication skills for producing research papers and thesis chapters.
How to apply
If you have any questions, contact the principal supervisor, Dr Muhammad Atif Ur Rehman .
To apply you will need to complete the online application form for a part time PhD in Computing & Digital Technology.
Please complete the Doctoral Project Applicant Form , and include your CV and a covering letter to demonstrate how your skills and experience map to the aims and objectives of the project, the area of research and why you see this area as being of importance and interest.
Please upload these documents in the supporting documents section of the University’s Admissions Portal or send them to the PGR Admissions team at pgradmissions@mmu.ac.uk .
Please quote the reference: SciEng-DTA Jan 2027-MR-AI Security UAV
Funding
GBP 31,236 per year
How to apply
- Read the full advert on the source site — it carries the authoritative terms.
- Email the contact below with your CV and a short, specific message. See Emailing Professors.
- Prepare your SOP, CV, transcripts and referees before the deadline.
- Apply through the university's own portal. Never pay a fee to a third party.