Secure and Trustworthy AI for Autonomous Vehicle Ecosystems

About the project

About the Project Supervisory Team: Dr Erisa Karafili This project develops AI-enhanced threat-modelling techniques to improve the cybersecurity and resilience of autonomous vehicles. It analyses vulnerabilities in AI-driven sensing and decision systems, models complex adversarial interactions, and designs adaptive detection and mitigation strategies, with applicability to other safety-critical domains. Autonomous vehicles increasingly depend on artificial intelligence to support perception, decision-making, and communication, introducing new and complex cybersecurity challenges. This project will investigate how advanced threat-modelling approaches can be used to improve the security and resilience of AI-enabled autonomous vehicle systems under adversarial conditions. The research will focus on analysing AI models deployed within autonomous vehicles to systematically identify and characterise potential attack surfaces. Particular attention will be given to threats that exploit learning-based components, including data poisoning, sensor manipulation, and model interference, as well as how such attacks propagate across interconnected vehicle subsystems. Building on this analysis, the project will develop a formal, multi-dimensional threat-modelling framework capable of representing interactions between physical, cyber, human, and AI elements, both within the vehicle and across its wider operational environment. A key aspect of the work will involve integrating AI-driven threat intelligence to support the automated extraction, classification, and prediction of emerging threats. The project will also explore adaptive security mechanisms that leverage threat-aware reasoning to detect anomalous behaviour and inform mitigation strategies, enhancing the robustness of onboard AI systems and decision-making processes. The developed methods will be evaluated using realistic autonomous vehicle scenarios and will be considered for transfer to other safety-critical domains. You'll have the opportunity to undertake an exciting industrial placement with a global automotive manufacturer, gaining hands-on experience with real-world autonomous vehicle security challenges and cutting-edge industrial research. Entry requirements You must have a UK first-class honours degree, or its international equivalent , in one of the following: cyber Security computer Science artificial Intelligence engineering a closely related discipline Essential skills: excellent programming skills (e.g. Python, C++, or similar) strong background in cyber security, including threat modelling and secure systems solid understanding of artificial intelligence and machine learning strong interest in autonomous vehicles and safety-critical systems Experience with adversarial machine learning or security of AI-enabled systems is desirable. This project is open to UK and Horizon Europe students only. Please note that applications will be considered as they are received, and this advert may close before the stated deadline if a suitable candidate is identified. Applicants are therefore encouraged to apply as early as possible. Fees and funding This is an IDLA EPSRC studentship with an industrial partner. This project is fully funded, including tuition fees and an enhanced stipend that exceeds the UKRI minimum. It also offers a generous allowance for travel, equipment, and laboratory consumables. How to apply Apply now You need to: choose programme type (Research), 2026/27, Faculty of Engineering and Physical Sciences select Full time or Part time search for programme PhD Computer Science (7089) add name of the supervisor in section 2 of the application Applications should include: research proposal your CV (resumé) 2 academic references degree transcripts and certificates to date English language qualification (if applicable) Contact us Faculty of Engineering and Physical Sciences If you have a general question, feps-pgr-apply@soton.ac.uk . Project leader For an initial conversation, E.Karafili@soton.ac.uk . The School of Electronics and Computer Science is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.

Research areas