Yuan Hong

Dr. Yuan Hong is an Associate Professor and Collins Aerospace Professor at the University of Connecticut's School of Computing, affiliated with the Connecticut Advanced Computing Center (CACC). He previously held an Assistant Professor position at Illinois Institute of Technology. His expertise spans Security, Privacy, and Trustworthy Machine Learning, with a focus on differential privacy, secure computation, adversarial attacks, and robustness in AI systems. He has received notable awards including the NSF CAREER Award and Cisco Research Awards, and his work has been published in top-tier venues like S&P, CCS, NeurIPS, and CVPR.

Education: Ph.D. (Rutgers University), M.Sc. (Concordia University), B.Sc. (Beijing Institute of Technology).

Research interests include adversarial machine learning, federated learning security, and privacy-preserving techniques. His recent work addresses challenges in machine unlearning, certified defenses, and robust watermarking for graph learning systems. He actively advises students (Ph.D., M.Sc., undergraduate) and leads the DataSec Lab. Current teaching includes Cybersecurity Lab, Computer Security, and Database Organization.

Awards include the CCS Distinguished Paper Award (2024) and the Taylor L. Booth Graduate Fellowship for a student. He organizes conferences such as WPES'22 and DBSEC'22, and serves on editorial boards for IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Information Forensics and Security, and others.

Key contributions include frameworks for certified adversarial robustness (e.g., UniCR), differential privacy mechanisms for federated learning, and defenses against poisoning attacks in video and code generation models.