Alessio Lomuscio

Alessio Lomuscio is a Professor of Safe Artificial Intelligence at Imperial College London, Department of Computer Science. His research focuses on the verification and assurance of AI-based systems, including validation of computer vision systems, robustness, certified learning, neurosymbolic systems, and logic-based specification and verification of autonomous systems. He leads the Safe AI Lab, where methods and tools for verifying AI systems are developed to ensure their safe and secure deployment in applications of societal importance. Current research areas include verification and robust learning for neural networks and decision trees, robust machine learning in aviation and finance, monitoring of machine learning systems, and assurance for autonomous systems and AI.

Alessio R Lomuscio is a researcher at Imperial College London, focusing on Safe AI, Verification, Robustness, Multi-Agent Systems, Machine Learning, and Logic. His work explores the verification of multi-agent systems, including model checking techniques for epistemic properties and strategy logic specifications. He has developed tools like MCMAS, an open-source model checker for multi-agent systems, and contributed to neural network verification through methods such as reachability analysis and adversarial search. His research also addresses negotiation in electronic commerce and formalisms for multi-agent systems, emphasizing logical foundations and computational methods for ensuring system correctness and robustness.