Ka-Ho Chow

Professor Ka-Ho Chow is an Assistant Professor in the Division of Computer Science, School of Computing and Data Science at The University of Hong Kong. His research lies at the intersection of machine learning, cybersecurity, and systems, with the overarching goal of amplifying the real-world impact of AI by building trustworthy and attack-resilient AI systems through an adversarial lens. His recent work focuses on understanding emerging security and privacy threats to modern AI systems—such as large language models, federated learning, and visual recognition pipelines—and on developing robust defenses through algorithmic design and infrastructure optimization. His research spans both centralized and federated learning settings, addressing challenges including backdoor attacks, gradient inversion, privacy leakage, and robustness of graph and vision models. Prior to joining HKU, Professor Chow was a research scientist at IBM Research. He received his Ph.D. in Computer Science from the Georgia Institute of Technology, where he was advised by Professor Ling Liu. His work has been published at leading venues including ICCV, ECCV, IJCAI, EuroSys, WWW, and top security conferences, and has received broad media coverage.