From Generative Pre-trained Models to Verifiable Protocols for Security and Privacy Preservation

From generative pre-trained models to verifiable protocols for security and privacy preservation

Ufuk Topcu, The University of Texas at Austin

This project investigates the suitability of recently developed techniques in the intersection of pre-trained generative models and formal methods for synthesizing verifiable strategies for sequential decision-making. It aims to demonstrate the utility in examples of protocols for preserving security and/or privacy, e.g., secure multi-party computation.

Ufuk Topcu is a Professor in the Department of Aerospace Engineering and Engineering Mechanics at The University of Texas at Austin, where he holds the Temple Foundation Endowed Professorship No. 1 Professorship. He is a core faculty member at Texas Robotics and the Oden Institute for Computational Engineering and Sciences and the director of the Autonomous Systems Group. His research focuses on the theoretical and algorithmic aspects of the design and verification of autonomous systems.