Roy Betser is a PhD candidate int he Technion and an AI security senior researcher in Fujitsu Research of Europe, where heis part of the GenAI Trust team. His research focuses on analyzing representation and embedding spaces in foundation models and on developing practical trust and safety mechanisms for agentic AI systems. He works on studying the geometry and statistics of learned latent spaces, developing methods for detecting and characterizing AI-generated content, and designing lightweight, deployable techniques for policy compliance and risk mitigation. His work aims to bridge theoretical insights about model behavior with robust engineering solutions for real-world AI deployment.
linkedin.com/in/roy-betser/
