Dr. Stefan Sarkadi is an interdisciplinary AI researcher. Currently, he is a Postdoctoral Researcher at King’s College London on the PRAISE project with Dr. Natalia Criado and Dr. Jose Such. He is also an Associate Researcher with the Wimmics and Hyper-Agents groups at Inria Sophia-Antipolis in France.

Stefan holds a PhD in Computer Science from King’s College London, a Master’s in Cognitive Science from the University of Edinburgh, and a Bachelor’s in Philosophy from the West University of Timisoara. Broadly, his areas of specialisation range from multi-agent systems, to agent based modelling, and knowledge representation and reasoning.

Stefan aims to understand the behaviour of intelligent agents (humans or machines) inside social environments like hybrid societies, and study their behaviour with respect to social norms and to ethical, legal, and safety standards. In particular, he is interested in the topics of deceptive machines, self-explainable AI agents with Theory-of-Mind, and the ability of AI agents to build stories and narratives.

Notably, Stefan’s PhD thesis, entitled “Deception”, is the first full computational treatment of deception in the area of AI. His PhD work on deception has been published in several top journals and conferences. Stefan has co-organised and chaired the first two iterations of the International Workshop on Deceptive AI co-located with ECAI2020 and IJCAI2021 and has edited the respective joint proceedings, which have been published as the Springer CCIS book on Deceptive AI.

Previously, Stefan was a 3IA Postdoctoral Fellow at Inria Sophia-Antipolis within the 3IA Côte d’Azur Institute. Before that, during his PhD at King’s, he was part of the Distributed AI Research Group and the Trusted Autonomous Systems Hub within the Department of Informatics, and of the Cyber Security Research Group within the Department of War Studies. During his PhD studies, he was also a visiting researcher at the MIT Media Lab in the Scalable Cooperation Group.