Federated Learning-Driven Decentralized AI Systems for Secure and Scalable Operations in Vehicular Networks

Autonomous vehicles and smart transportation systems rely on artificial intelligence (AI) to process vast amounts of real-time data. Traditional AI models follow a central data collection approach, where raw data from multiple vehicles is continuously transmitted to a remote server for training and decision-making. This method introduces critical concerns. For example, privacy is compromised as sensitive data, including vehicle location, driving patterns, and sensor readings. Centralized storage also presents security risks, making data more vulnerable to cyberattacks and unauthorized access. Moreover, transmitting large datasets leads to high communication costs, increased bandwidth consumption, and potential delays in real-time decision-making.

This project aims to overcome these challenges by developing a federated learning-driven AI system that enables vehicles to collaboratively train models while keeping their data localized. By eliminating the need for centralized data transfer, federated learning preserves privacy, mitigates cybersecurity threats, and reduces communication overhead. However, real-world deployment comes with additional complexities, such as integrating diverse sensor data, optimizing AI models for vehicles with limited computing resources, and ensuring fast and reliable inter-vehicle communication.

The research will focus on designing privacy-preserving AI models and enhancing the efficiency of distributed learning in vehicular networks. It will integrate techniques from machine learning, deep learning, and network optimization to develop a scalable and secure AI framework for smart transportation. The successful candidate will work with experienced researchers, gain access to state-of-the-art computing resources, and contribute to high-impact publications. This project offers an exciting opportunity to develop AI-driven solutions that enhance autonomous driving, traffic safety, and smart mobility, shaping the future of intelligent transportation.

Applicants should have a first or upper second class honours degree in an appropriate subject and preferably a relevant Masters qualification. Applications from both UK and overseas students are welcome.

The studentship is supported for 3.5 years and includes full Home tuition fees, Bench fee plus a stipend of £20,780 per annum 2025/26 rate. The studentship will only fully fund those applicants who are eligible for Home fees with relevant qualifications. Applicants normally required to cover International fees will have to cover the difference between the Home and the International tuition fee rates. The international component of the fee may be waived for outstanding international applicants.

There is no additional funding available to cover NHS Immigration Health Surcharge (IHS) costs, visa costs, flights etc.

NB: The studentship is supported for 3.5 years of the four-year registration period. The subsequent 6 months of registration is a self-funded ‘writing-up’ period.

If you wish to discuss this project further informally, please contact Muhammad.asad@plymouth.ac.uk.

Please see our apply for a postgraduate research programme page for a list of supporting documents to upload with your application.

For more information on the admissions process generally, please contact research.degree.admissions@plymouth.ac.uk.

The closing date for applications is 12 noon on 28 March 2025. Shortlisted candidates will be invited for interview shortly thereafter. We regret that we may not be able to respond to all applications. Applicants who have not received a response within six weeks of the closing date should consider their application has been unsuccessful on this occasion.