Job description
Supervisory Team: Richard Guest and Jennifer Williams Project Description: Increasingly AI-based biometric technologies, such as facial recognition and voice biometrics, are playing a major role in assisting public authorities to protect the public, reduce serious crime, and help safeguard vulnerable persons. From a technical perspective, there are challenges concerning the use of AI-based biometric systems for law enforcement purposes. Specifically, there is the opaque operation of these systems, including what training datasets are used, the risk of those datasets being unfairly biased, and how exactly these automated decisions and recommendations are being made to public authorities. Working alongside Professor Richard Guest and Dr Jennifer Williams in the School of Electronics and Computer Science, this project will look at the explainability of AI-based biometrics systems. The project will: Scrutinise the performance of open deep-learning architectures in facial and voice biometric modalities, assessing the decision-making process using state of the art trustworthy AI analysis tools, extending their functionality where necessary. This objective will be assessed by the production of an open-source analysis methodology and software tools for describing a decision outcome generic to a range of widely used deep-learning-based biometric systems. Explore if Generative AI ‘spoofed’ media be detected through the use of xAI? Explore differences within a series of deep-learning architectures to identify any performance bias within a series of sub-populations and explain judgment characteristics of a particular population. This objective will be assessed through the production of policy documents and analysis on population subgroups using our software tools and methods. If you wish to discuss any details of the project informally, please contact Professor Richard Guest, Cyber Security Research Group, Email: r.m.guest@soton.ac.uk. Entry Requirements A very good undergraduate degree (at least a UK 2:1 honours degree, or its international equivalent). Closing Date: 31 August 2024. Applications will be considered in the order that they are received, the position will be considered filled when a suitable candidate has been identified. Funding: We offer a range of funding opportunities for both UK and international students, including Bursaries and Scholarships. For more information please visit PhD Scholarships | Doctoral College | University of Southampton. Funding will be awarded on a rolling basis, so apply early for the best opportunity to be considered. How To Apply Apply online: HERE Select programme type (Research), 2024/25, Faculty of Engineering and Physical Sciences, next page select “PhD Computer Science (Full time)”. In Section 2 of the application form you should insert the name of the supervisor Richard Guest. Applications should include: Research Proposal Curriculum Vitae Two reference letters Degree Transcripts/Certificates to date The School of Electronics & 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.
Address
Form of work
Southampton, Hampshire
