Lucas Fenaux

Status

• 3rd year Computer Science PhD. candiate at the University of Waterloo. Member of the CrySP lab under the supervision of Florian Kerschbaum.

• Graduated from my Master's of Math at the University of Waterloo January 2024. Member of the CrySP lab under the supervision of Florian Kerschbaum.

Recent Publications

• Under submission:

  • Hammer and Anvil: Toward a Theory of Backdoors in Federated Learning.

  • Private Vertical Federated Inference for Time-Series.

• AAMAS 2026:

  • On the Trade-Off Between Transparency and Security in Adversarial Machine Learning.

• USENIX 2024: 

  • Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions.

• ICLR 2024: Leveraging Optimization for Adaptive Attacks on Image Watermarks.

• GECCO 2023: Gaggle: Genetic Algorithms on the GPU using PyTorch. 

Current Research Areas

• Private and Secure Distributed Machine Learning

• Federated Learning Security

• World Model Security

• Adversarial Machine Learning