معرفی
Dr. Stefan Sarkadi is a Research Fellow at King's College London and Royal Academy of Engineering UK Intelligence Community Research Fellow, leading the HIDE Lab focused on deceptive AI research. He holds an Associate Researcher position at Inria Sophia-Antipolis and is a faculty affiliate at Ontario Tech's Trustworthy AI Lab.
Education: PhD in Computer Science (King's College London), MSc in Cognitive Science (Edinburgh), B.A. in Philosophy (West University of Timisoara).
Research interests include deceptive AI, multi-agent systems, self-explainable AI, and ethical implications of AI. His work addresses deception analysis through storytelling AI and integrates AI with socio-cognitive phenomena.
Received the Royal Academy of Engineering fellowship for enhancing deception analysis with AI storytelling. Over 30 peer-reviewed publications in top conferences like AAMAS and AAAI, with focus on multi-agent systems, argumentation frameworks, and ethical AI.
Teaching experience includes co-organizing King's Agents and Multi-Agent Systems module, receiving teaching awards for innovative pedagogy. Supervises PhD students in AI ethics and deception modeling.
Leads HIDE Lab exploring AI's role in deception detection and mitigation, collaborating on projects like self-governing hybrid societies and privacy-enhanced AI assistants.
