Carnegie Mellon University
About Me
I am a 5th year Societal Computing PhD student in the School of Computer Science at Carnegie Mellon University, advised by Lujo Bauer. I am a member of CyLab, the security and privacy institute at CMU.
My research focuses on problems at the intersection of machine learning, security, and cyber-physical systems. Currently, I am investigating novel techniques for ML-based anomaly detection in industrial control systems. Some of my past research projects include (i) client-side, ML-based detection of DOM-XSS vulnerabilities and (ii) attacks and defenses for multi-party federated learning systems.
I finished my M.Sc. in computer science in 2018 at the University of British Columbia, where I was a member of the Networks, Systems and Security (NSS) Lab. I built systems for private and secure multi-party machine learning with Ivan Beschastnikh, to whom I owe a great deal.
Even more before that, I finished my B.A.Sc. Systems Design Engineering in 2016 at the University of Waterloo, with several internships spanning a wide variety of projects: from developing tools for bio-informatics research to building large-scale, online machine learning infrastructure with LinkedIn.
I currently maintain the Security and Privacy Conference Deadlines webpage.
Contact
Email : clementf [at] andrew [dot] cmu [dot] edu
Physical : CIC 2223B
Recent News
- 10/2023 [Paper]: Released a new pre-print based on work done during my summer internship at Bosch: "Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data".
- 08/2023 [Paper]: "Attributions for ML-based ICS Anomaly Detection: From Theory to Practice" accepted at NDSS 2024!
- 05/2023 [Work]: This summer, I am interning at the Bosch Center for AI in Pittsburgh!
- 05/2023 [Misc]: Attending CACTUS-P at the University of Maryland in College Park! Find me if you want to chat about human interaction with anomaly detection!
- 04/2023 [Misc]: Presented my research on industrial anomaly detection at a CAE-R research seminar.
- 02/2023 [Service]: Serving as a PC member for FAccT '23!
- Older news
Happy to Connect!
Copyright © Clement Fung