no code implementations • 25 Jul 2023 • Oualid Zari, Javier Parra-Arnau, Ayşe Ünsal, Melek Önen
Furthermore, we examine the application of differential privacy (DP) mechanisms to mitigate the impact of our proposed attack, we analyze the trade-off between privacy preservation and model utility.
no code implementations • 5 Jul 2023 • Oubaïda Chouchane, Michele Panariello, Oualid Zari, Ismet Kerenciler, Imen Chihaoui, Massimiliano Todisco, Melek Önen
In this paper, we present an adversarial Auto-Encoder--based approach to hide gender-related information in speaker embeddings, while preserving their effectiveness for speaker verification.
1 code implementation • 31 Oct 2021 • Oualid Zari, Chuan Xu, Giovanni Neglia
In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally.