Research Associate in Secure and Privacy-preserving AI models

at  The University of Manchester

This role is for a Research Associate to conduct advanced research in secure and privacy-preserving AI models as part of the EnnCore project (https://enncore.github.io/ ).
The EnnCore project will address a fundamental security problem in neural-based (NB) architectures, allowing system designers to specify and verify a conceptual/behavioural hardcore to the system, which can be used to safeguard NB systems against unexpected behaviour and attacks. It will pioneer the dialogue between contemporary explainable neural models and full-stack neural software verification. We will, therefore, develop methods, algorithms and tools to achieve fully-verifiable intelligent systems, which are explainable, whose correct behaviour is guaranteed, and that are privacy-preserving and robust towards attacks.
Manchester has a long and distinguished track record in researching core Computer Science and across interfaces to adjacent disciplines. Founded upon the pioneering work of Williams, Kilburn and Turing, the Department was the first academic Department of Computer Science in the UK and one of the first to run an undergraduate programme. The research strength of the school is reflected in consistently strong returns in UK research assessment exercises (5* in RAE 2000, 2nd in Research Power in RAE 2008, 4th in overall GPA in REF 2014 and ranked equal 1st for research environment). The Systems and Software Security (S3) has a broad range of expertise, including developing system design and verification methods, and application of privacy enhancing technologies.
With its focus on real-world use cases, this position is a unique opportunity to make a real impact, advance state-of-the-art in applied privacy-preserving AI research, and join a top-class team of collaborators. The role also offers an outstanding opportunity for career development that is equally well-suited to an academic or industrial research path or subsequent work as a privacy engineer in the industry.
The post holder will be a member of the EnnCore team, working closely with Dr Mustafa Mustafa and Dr Lucas Cordeiro at Manchester. The ideal candidate will research and apply novel privacy-preserving theories and methodologies on real-world use cases being investigated in the project. In particular, the candidate will enjoy designing, developing and evaluating novel AI models (deep neural networks) that are privacy-preserving and robust against attacks. The project will involve the continuous interaction with experts in explainable AI and formal software verification. They will also have the opportunity to build use cases and to collaborate with domain experts in areas such as cancer research and energy trading. The candidate will design, develop and evaluate new models in the context of their accuracy, privacy-protection and robustness. This position may include research on a diverse set of techniques such as federated learning, homomorphic encryption, multiparty computation and adversarial methods.
As a result, the successful candidate will collaborate with researchers at the University of Manchester. The post holder will also closely interact with the research term at the university of Liverpool, working on technology aimed at real-world impact.

What you will get in return:

• Fantastic market leading Pension scheme
• Excellent employee health and wellbeing services including an Employee Assistance Programme
• Exceptional starting annual leave entitlement, plus bank holidays
• Additional paid closure over the Christmas period
• Local and national discounts at a range of major retailers

As an equal opportunities employer we welcome applicants from all sections of the community regardless of age, sex, gender (or gender identity), ethnicity, disability, sexual orientation and transgender status. All appointments are made on merit.
Our University is positive about flexible working you can find out more here
Hybrid working arrangements may be considered.
Please note that we are unable to respond to enquiries, accept CVs or applications from Recruitment Agencies.
Any recruitment enquiries from recruitment agencies should be directed to People.Recruitment@manchester.ac.uk.
Any CV’s submitted by a recruitment agency will be considered a gift.

Please refer the Job description for details