Clement Fung
Postdoctoral Researcher
Carnegie Mellon University

About Me

📢 I will be joining the UMBC Department of Computer Science and Electrical Engineering as a tenure-track assistant professor in Fall 2026. If you are interested in collaborating, please reach out!

I am currently a postdoctoral research associate in the Software and Societal Systems Department in the School of Computer Science at Carnegie Mellon University, where I recently defended my Ph.D. (Fall 2025) in Societal Computing, advised by Lujo Bauer. I am a member of CyLab, the security and privacy institute at CMU.

My research interests are at the intersection of security, machine learning (ML), and cyber-physical systems. My Ph.D. thesis proposes ML-based techniques and guidelines for making anomaly-detection systems more effective at securing industrial control systems (ICS). This involves:

  • Evaluating which models and techniques perform best (ESORICS '22)
  • Designing attribution methods to aid with anomaly diagnosis (NDSS '24)
  • Interviewing practitioners to understand needs and opportunities for ML in ICS (SOUPS '25)
My other research projects include:
  • Data augmentation techniques to improve anomaly detection systems (TAI '25, IROS '24)
  • ML-based DOM-XSS vulnerability detection (WWW '21)
  • Attacks and defenses for multi-party federated learning systems (TPDS '21, RAID '20)

I finished my M.Sc. (2018) in Computer Science at the University of British Columbia, as a member of the Networks, Systems and Security (Systopia) Lab. I built systems for private and secure multi-party machine learning with Ivan Beschastnikh.

I finished my B.A.Sc. (2016) in Systems Design Engineering at the University of Waterloo, which included multiple internships spanning a variety of projects: from developing tools for bio-informatics research to building online machine-learning infrastructure at LinkedIn.

I also help maintain the Security and Privacy Conference Deadlines webpage.

Contact

Email : clementf [at] andrew [dot] cmu [dot] edu
Physical : CIC 2207

Recent News

  • 05/2026 [Service]: Serving as a PC member for RAID 2026.
  • 02/2026 [Service]: Serving as a PC member for CPSS 2026, ACM SoCC 2026, and VehicleSec 2026.
  • 11/2025 [Paper]: Published a new arXiv preprint from work led by multiple undergraduate and masters students: Attacking Autonomous Driving Agents with Adversarial Machine Learning: A Holistic Evaluation with the CARLA Leaderboard. Thank you for all your hard work!
  • 10/2025 [Award]: I won a PhD Student Research Award at RSTCON 2025 and will be speaking in Savannah, GA!
  • 09/2025 [Misc]: I have defended my PhD thesis at CMU! Thank you to my thesis committee and my collaborators for all their support!
  • 08/2025 [Talk]: Speaking at SOUPS 2025 and presenting a research poster at USENIX Security 2025 in Seattle!
  • 05/2025 [Paper]: "Adopting AI to Protect Industrial Control Systems: Assessing Challenges and Opportunities from the Operators' Perspective" accepted at SOUPS 2025!
  • 04/2025 [Paper]: "Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data" accepted in IEEE Transactions on Artificial Intelligence (TAI)!
  • 03/2025 [Service]: Serving as a PC member for RAID 2025 and ISC 2025.
  • 01/2025 [Misc]: Officially completed the CMU Eberly Future Faculty Program, a program designed to help students develop teaching skills in preparation for a faculty career. Thank you to the Eberly consultants who helped me throughout the process!
  • 11/2024 [Award]: Best Poster Award at the 2024 IAP CMU Workshop on the Future of AI and Security in the Cloud!
  • 10/2024 [Talk]: With funding from the DAAD AINet Fellowship, I visited Germany and gave research talks at KIT, MPI-SWS, and CISPA. Thank you to the faculty who hosted me and to all who met with me!
  • 10/2024 [Talk]: Presented an overview of my dissertation at a CAE-R Research Symposium as part of the 2024 National Cybersecurity Education Colloquium in St. Louis!
  • Older news

Happy to Connect!

Github

LinkedIn

Last Updated: May 13th, 2026
Copyright © Clement Fung