Artificial Intelligence

Resilient defence sensing: adaptive modelling for trust, compromise, and coalition detection

University of Southampton

Faculty of Engineering and Physical Sciences

Location
Southampton, United Kingdom, United Kingdom
Funding
Competition Funded PhD Project (Students Worldwide)
Application deadline
31 October 2026

About the project

About the Project Supervisory Team: Dr Erisa Karafili and Enrico Gerding The project investigates how distributed sensing systems can remain trustworthy and operational when facing intelligent, coordinated adversaries. It develops an AI-driven trust scoring framework to detect compromised and colluding sensors, enhancing resilience, accuracy, and decision-making in critical defence sensing applications. This project, a collaboration between the University of Southampton and Thales UK, explores how future defence and security sensing systems can remain reliable in the presence of faults, manipulation, and intelligent adversaries. Modern sensing systems increasingly rely on large, distributed networks combining physical sensors, cyber data, and open-source intelligence, making them vulnerable to degradation, spoofing, misinformation, and coordinated attacks. The research will develop an AI-driven trust scoring framework that continuously evaluates the reliability of individual sensors and identifies groups of sensors that may be colluding to influence system decisions. By combining anomaly detection, adversarial modelling, and data provenance analysis, the framework will assess sensor behaviour in real time and adapt to changing threat conditions. The project will also investigate the use of game-theoretic techniques to anticipate and respond to evolving adversarial strategies. The proposed methods will be evaluated under realistic attack scenarios, including sensor tampering, spoofing, misinformation, and coordinated coalition attacks. The outcome will be a scalable decision-support framework that improves the resilience, accuracy, and trustworthiness of distributed sensing systems, with applications in critical defence and security environments. The successful candidate will have the exciting opportunity to undertake a three-month industrial placement with Thales UK cortAIx Labs based at their Research, Technology and Solution Innovation centre in Reading, gaining hands-on experience and exposure to real-world defence and security challenges. Entry requirements You must have a 1st class honours degree, or its international equivalent , in computer science mathematics engineering or a closely related discipline. Essential requirements: excellent programming skills (e.g. Python, C++, or similar) strong mathematical background, particularly in probability, statistics, and optimisation solid knowledge of artificial intelligence and machine learning keen interest in cyber security and adversarial systems Experience with game theory, adversarial modelling, or distributed and sensing systems is desirable. Candidates should be highly motivated and capable of independent research. This project is open to UK and Horizon Europe nationals, and as part of this role, you may be required to obtain UK Security Clearance. Fees and funding This is an IDLA Scholarship funded by Thales UK and EPSRC. This project is sponsored by Thales UK, enabling an enhanced stipend (~£6,250 per year above the UKRI minimum). In addition, the student will benefit from a generous allowance for travel, equipment, and lab consumables. We offer a range of funding opportunities for UK and Horizon Europe students. Competition-based studentships offered by our schools typically cover UK-level tuition fees and a stipend for living costs for top-ranked applicants. Funding will be awarded on a rolling basis, so apply early for the best opportunity to be considered. For more information, please visit our postgraduate research funding pages. 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, email e.karafili@soton.ac.uk .

Research areas

ArtificialIntelligenceCyberSecurityResilientdefencesensing:adaptivemodellingfortrust,compromise,andcoalitiondetection