Research Blog

DEIS research presented at Computing Conference 2026 explores how generative AI can create formal safety artefacts, including fault trees, while keeping engineering evidence transparent and open to verification.

Dr Zhibao Mian presented DEIS research on generative AI for formal safety artefacts during the Applied AI session at Computing Conference 2026.

Artificial intelligence (AI) systems are becoming increasingly integrated into critical areas such as healthcare, transportation, finance, and manufacturing. As these systems take on more complex and impactful roles, ensuring their safety and reliability becomes essential. SafeML, a framework designed for safety monitoring of AI, offers a promising approach to address this challenge. This post explores the concept of SafeML, its key features, methodologies, and applications a

Professor Yiannis Papadopoulos discusses how safe AI, optimisation and large language models could improve fleet service, maintenance and repair.

Dr Koorosh Aslansefat’s MSSiS 2025 keynote introduced SafeML and SMILE for runtime safety monitoring and model-agnostic explainability.

Q-SafeML extends runtime statistical safety monitoring to quantum machine learning, tracking distribution shifts, behavioural change and uncertainty.

On 22–23 June 2026, the Marine Robotics and Intelligent Systems group at the Universitat de les Illes Balears hosted the OCTOPUS Workshop 2026 in Palma de Mallorca. The event brought together researchers from Université Le Havre Normandie, the University of Hull, and Inha University to discuss progress, exchange ideas, and shape the next phase of collaboration.

Safety of Machine Learning with SafeML SafeML will be useful to you if you develop a dependable system with components that employ Machine Learning (ML). A key question that you may wish to address is whether and when the reasoning of these components can be trusted. Imagine that you design an autonomous car, and you wish to incorporate an ML system that uses a camera to read the state of traffic lights. You may have trained this system extensively with large volumes of da