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 (NDSS '24, ESORICS '22). Some of my past research projects include (i) client-side, ML-based detection of DOM-XSS vulnerabilities (WWW '21) and (ii) attacks and defenses for multi-party federated learning systems (TPDS '21, RAID '20).

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 (Systopia) Lab. I built systems for private and secure multi-party machine learning with Ivan Beschastnikh, to whom I owe a great deal.

I finished my B.A.Sc. in Systems Design Engineering in 2016 at the University of Waterloo, with multiple internships spanning a wide variety of projects: from developing bio-informatics research tools to building large-scale, online machine-learning infrastructure at 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

• 07/2024 [Misc]: Passed my Thesis Proposal! Thank you to the audience and committee for their feedback!
• 07/2024 [Paper]: "Targeted Image Transformation for Improving Robustness in Long Range Aircraft Detection" accepted at IROS 2024!
• 05/2024 [Misc]: Attending Hack the Capitol 7.0 in Washington, DC to share my research in ICS security with government and industry!
• 04/2024 [Award]: I have been selected as a 2024 DAAD AINet Fellow! The focus area for this year's fellowship was "Safety and Security in AI".
• 02/2024 [Talk]: Presenting at NDSS 2024 in San Diego!
• 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!
• Older news

Happy to Connect!

Github

Twitter

LinkedIn

Flickr

Lastfm