Clement Fung
PhD Student
Carnegie Mellon University

Selected Publications


Targeted Image Transformation for Improving Robustness in Long Range Aircraft Detection
Rebecca Martin, Clement Fung, Nikhil Keetha, Lujo Bauer, Sebastian Scherer.
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)
Abu Dhabi, UAE. October 2024.
[PDF]


Attributions for ML-based ICS Anomaly Detection: From Theory to Practice
Clement Fung, Eric Zeng, Lujo Bauer.
31st Network and Distributed System Security Symposium (NDSS 2024)
San Diego, CA, USA. February 2024.
[PDF] [Video] [Slides] [Code]


Perspectives from a Comprehensive Evaluation of Reconstruction-based Anomaly Detection in Industrial Control Systems
Clement Fung, Shreya Srinarasi, Keane Lucas, Hay Bryan Phee, Lujo Bauer.
27th European Symposium on Research in Computer Security (ESORICS 2022)
Copenhagen, Denmark. September 2022.
[PDF] [Springer] [Video] [Slides] [Code]


Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning
Muhammad Shayan, Clement Fung, Chris J.M. Yoon, Ivan Beschastnikh.
IEEE Transactions on Parallel and Distributed Systems (TPDS)
Volume 32, Issue 7. July 2021.
[PDF] [IEEE] [Code]


Towards a Lightweight, Hybrid Approach for Detecting DOM XSS Vulnerabilities with Machine Learning
William Melicher, Clement Fung, Lujo Bauer, Limin Jia.
The Web Conference 2021
Ljubjana, Slovenia (Virtual). April 2021.
[PDF] [Video] [Code]


The Limitations of Federated Learning in Sybil Settings
Clement Fung, Chris J.M. Yoon, Ivan Beschastnikh.
23rd International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2020)
Donostia/San Sebastian, Spain (Virtual). October 2020.
[PDF] [Video] [Slides] [Code]


Brokered Agreements in Multi-Party Machine Learning
Clement Fung, Ivan Beschastnikh.
10th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys 2019)
Hangzhou, China. August 2019.
[PDF] [ACM] [Slides] [Code]


GainForest: Scaling Climate Finance for Forest Conservation using Interpretable Machine Learning on Satellite Imagery
David Dao, Catherine Cang, Clement Fung, Ming Zhang, Nick Pawlowski, Reuven Gonzales, Nick Beglinger, Ce Zhang.
Climate Change: How Can AI Help?: ICML 2019 Workshop
Long Beach, CA, USA. June 2019.
[PDF] [Poster]

Pre-prints


Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data
Clement Fung, Chen Qiu, Aodong Li, Maja Rudolph.
arXiv preprint 2310.10461, October 2023.
[PDF]


Dancing in the Dark: Private Multi-Party Machine Learning in an Untrusted Setting
Clement Fung, Jaime Koerner, Stewart Grant, Ivan Beschastnikh.
arXiv preprint 1811.09712, November 2018.
[PDF] [Code]


Mitigating Sybils in Federated Learning Poisoning
Clement Fung, Chris J.M. Yoon, Ivan Beschastnikh.
arXiv preprint 1808.04866, August 2018.
[PDF] [Code]

Talks Given


Approaches for More Effective ML-based Anomaly Detection in Industrial Control Systems

  • Secure Cyber-Physical Systems Group, CISPA Helmholtz Center for Information Security. October 2024.
  • SysNets Seminar, Max Planck Institute for Software Systems. October 2024.
  • Artificial Intelligence and Security Group, Karlsruhe Institute of Technology. October 2024.
  • CAE-R Research Symposium, National Cybersecurity Education Colloquium. October 2024.

Attributions for ML-based ICS Anomaly Detection: From Theory to Practice

  • Network and Distributed System Security Symposium (NDSS). February 2024. [Video]

Perspectives from a Comprehensive Evaluation of Reconstruction-based Anomaly Detection in Industrial Control Systems

  • CAE-R Seminar, April 2023. [Video]
  • European Symposium on Research in Computer Security (ESORICS). September 2022. [Video]

Detecting and Explaining Anomalies in Industrial Control

  • Bosch Center for Artificial Intelligence. June 2023.
  • Accountable Systems Lab, CMU. November 2022.
  • CyLab Partners Conference. October 2022.

Towards a Lightweight, Hybrid Approach for Detecting DOM XSS Vulnerabilities with Machine Learning

  • The Web Conference. April 2021. [Video]

The Limitations of Federated Learning in Sybil Settings

  • Symposium on Research in Attacks, Intrusions and Defenses (RAID). October 2020. [Video]

Brokered Agreements in Multi-Party Machine Learning

  • Asia-Pacific Workshop on Systems (APSys). August 2019.

Dancing in the Dark: Private Multi-Party Machine Learning in an Untrusted Setting