Posted: 10th April 2025

Department researchers are leading a major project as part of the UK Government’s Advanced Research and Invention Agency (ARIA) Safeguarded AI programme, which is investing in new technical approaches to the safe deployment of AI. 

The initiative supports nine research teams across the UK under Technical Area 3 (TA3), which focuses on developing mathematical and computational methods to provide quantitative safety guarantees for AI systems. The programme is led by David ‘davidad’ Dalrymple and forms part of ARIA’s broader £59 million Safeguarded AI investment. 

Towards Large-Scale Validation of Business Process Artificial Intelligence (BPAI) 
Led by Professors Nobuko Yoshida and Dave Parker, this project will provide formal, quantitative guarantees for AI-based systems in Business Process Intelligence (BPI). Using probabilistic process models and the PRISM verification toolset, the team will develop a workflow to analyse automated BPI solutions and evaluate them against safety benchmarks. Senior Research Associate Dr Adrián Puerto Aubel and Research Associate Joseph Paulus also contribute to the project, which will involve collaboration with industry to apply the methods in practical settings. 

Through the Safeguarded AI programme, ARIA is creating space to explore rigorous, formal approaches to AI safety. Our project addresses the challenge of verifying AI-based business process systems using probabilistic models and automated analysis techniques. By developing scalable workflows and benchmarks, we aim to provide quantitative guarantees that support the safe deployment of these systems in real-world settings. Professors Nobuko Yoshida and Dave Parker

ARIA’s Safeguarded AI programme supports the development of AI systems with rigorous safety guarantees, aiming to ensure that advanced AI can be deployed responsibly in domains such as infrastructure, healthcare, and manufacturing. 

More information is available on the ARIA website: https://www.aria.org.uk/opportunity-spaces/mathematics-for-safe-ai/safeguarded-ai/technical-areas