About the project
This project tackles cybersecurity challenges in AI-powered autonomous vehicles, particularly smart cars. It analyses vulnerabilities in AI models, develops a classification system for cyber threats, and creates a mitigation framework. The research aims to improve resilience, enable safe real-time operation, and set best practices for embedding cybersecurity into AI.
Autonomous vehicles, especially smart cars, are advancing rapidly through the integration of Artificial Intelligence (AI). These innovations bring significant benefits in safety and efficiency but also introduce critical cybersecurity risks. AI models are vulnerable to attacks such as sensor spoofing, data manipulation, and network intrusions, which can compromise safety, disrupt operations, and undermine public trust. Ensuring the resilience of AI-based systems against such threats is vital for the secure deployment of autonomous vehicles.
This project focuses on analysing, classifying, and mitigating cyber risks in AI-driven vehicles to strengthen their defences against evolving attacks. The research is structured around three key objectives:
- AI model vulnerability analysis: perform in-depth analysis of AI models in autonomous vehicles, focusing on weaknesses in data processing, decision-making, and response to cyber-attacks such as sensor spoofing and network intrusions
- threat classification and categorization: develop a systematic classification of cyber threats targeting AI systems, categorizing them by model behaviour and system weaknesses to predict attack vectors and improve understanding of risks
- security and mitigation framework development: design a robust framework with mitigation strategies, including real-time threat detection and resilience-enhancing measures, ensuring AI models maintain safe and uninterrupted operation under cyber-attacks
The overall aim is to enhance the resilience and safety of AI systems in autonomous vehicles. Beyond improving smart cars, this project will establish best practices for embedding cybersecurity into AI development, providing transferable guidelines to other safety-critical domains such as healthcare, aviation, and industrial automation.
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.
