PhD Studentship: Securing computing systems for business resilience in the Gen AI Era

Join a world-leading, cross-continental research team

The University of Exeter and the University of Queensland are seeking exceptional students to join a world-leading, cross-continental research team tackling major challenges facing the world’s population in global sustainability and wellbeing as part of the QUEX Institute. The joint PhD programme provides a fantastic opportunity for the most talented doctoral students to work closely with world-class research groups and benefit from the combined expertise and facilities offered at the two institutions, with a lead supervisor within each university. This prestigious programme provides full tuition fees, stipend, travel funds and research training support grants to the successful applicants.  The studentship provides funding for up to 42 months (3.5 years).

Project Description

Computing systems today face increasing security threats, including zero-day vulnerabilities, side-channel attacks, and firmware exploits across multiple layers. Traditional methods like signature-based detection and manual penetration testing struggle to keep up with evolving cyber threats targeting microarchitecture and system-level vulnerabilities. The attack surface expands rapidly with new software, hardware, and AI-integrated vulnerabilities, introducing novel attack vectors. For instance, an untrusted OS attacking protected software (Software-on-software attack), an untrusted software using cache side-channels to extract secrets (Software-on-hardware attack), a rogue memory controller exploiting DRAM via Rowhammer (Hardware-on-software attack), and a malicious peripheral disabling memory encryption (Hardware-on-hardware attack). Integration of AI introduces additional vulnerabilities across security domains, affecting malware detection and vulnerability discovery. Conventional mitigation techniques focus on specific vulnerabilities rather than a system-wide approach, often sacrificing performance.

This research aims to balance security and performance by advocating for AI-driven runtime detection-based mitigation. The candidate will design techniques for automated assessment of attack surfaces and vulnerabilities across software/hardware layers.

Advert information