Abdulrahman Diaa

According to our database, Abdulrahman Diaa authored at least 6 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of three.

2024

Optimizing Adaptive Attacks against Content Watermarks for Language Models.

Abdulrahman Diaa, Toluwani Aremu, Nils Lukas

CoRR, 2024

FastLloyd: Federated, Accurate, Secure, and Tunable k-Means Clustering with Differential Privacy.

Abdulrahman Diaa, Thomas Humphries, Florian Kerschbaum

CoRR, 2024

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

Abdulrahman Diaa, Lucas Fenaux, Thomas Humphries, Marian Dietz, Faezeh Ebrahimianghazani, Bailey Kacsmar, Xinda Li, Nils Lukas, Rasoul Akhavan Mahdavi, Simon Oya, Ehsan Amjadian, Florian Kerschbaum

Proceedings of the 33rd USENIX Security Symposium, 2024

Leveraging Optimization for Adaptive Attacks on Image Watermarks.

Nils Lukas, Abdulrahman Diaa, Lucas Fenaux, Florian Kerschbaum

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Privacy-Preserving Federated Recurrent Neural Networks.

Sinem Sav, Abdulrahman Diaa, Apostolos Pyrgelis, Jean-Philippe Bossuat, Jean-Pierre Hubaux

Proc. Priv. Enhancing Technol., October, 2023

HE is all you need: Compressing FHE Ciphertexts using Additive HE.

Rasoul Akhavan Mahdavi, Abdulrahman Diaa, Florian Kerschbaum

CoRR, 2023