My name is Abdulrahman Diaa. I am a Ph.D. student under the supervision of Florian Kerschbaum. I’m also a member of the Cryptography, Security, and Privacy (CrySP) lab at the University of Waterloo.
I hold a Masters degree in Computer Science from the University of Waterloo and a Bachelor of Science in Computer Engineering and Mathematics from The American University in Cairo.
Research
My research interests include privacy-preserving computation, fully homomorphic encryption, and differential privacy. I have also worked on projects related to trust-worthy machine learning. My current focus is on designing private and efficient protocols for emerging machine learning applications.
Preprints
A. Diaa, T. Humphries, and F. Kerschbaum.
FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy.
RA. Mahdavi, A. Diaa, and F. Kerschbaum.
HE is all you need: Compressing FHE Ciphertexts using Additive HE.
Publications
N. Lukas, A. Diaa, L. Fenaux, and F. Kerschbaum.
Leveraging Optimization for Adaptive Attacks on Image Watermarks.
International Conference on Learning Representations (ICLR), 2024.
A. Diaa, L. Fenaux, T. Humphries, M. Dietz, F. Ebrahimianghazani, B. Kacsmar, X. Li, N. Lukas, RA. Mahdavi, S. Oya, E. Amjadian, and F. Kerschbaum.
Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions.
Usenix Security Symposium, 2024.
S. Sav, A. Diaa, A. Pyrgelis, J. Boussat, and J. Hubaux.
Privacy-Preserving Federated Recurrent Neural Networks.
Proceedings on Privacy Enhancing Technologies (PoPETs), 2023.