On the resilience of Collaborative Learning-based Recommender Systems Against Community Detection Attack

no code implementations • 15 Jun 2023 • Yacine Belal, Sonia Ben Mokhtar, Mohamed Maouche, Anthony Simonet-Boulogne

This attack enables an adversary to identify community members based on a chosen set of items (eg., identifying users interested in specific points-of-interest).

Community Detection Federated Learning +1

Differentially Private Speaker Anonymization

no code implementations • 23 Feb 2022 • Ali Shahin Shamsabadi, Brij Mohan Lal Srivastava, Aurélien Bellet, Nathalie Vauquier, Emmanuel Vincent, Mohamed Maouche, Marc Tommasi, Nicolas Papernot

We remove speaker information from these attributes by introducing differentially private feature extractors based on an autoencoder and an automatic speech recognizer, respectively, trained using noise layers.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

The VoicePrivacy 2020 Challenge: Results and findings

1 code implementation • 1 Sep 2021 • Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Jose Patino, Brij Mohan Lal Srivastava, Paul-Gauthier Noé, Andreas Nautsch, Nicholas Evans, Junichi Yamagishi, Benjamin O'Brien, Anaïs Chanclu, Jean-François Bonastre, Massimiliano Todisco, Mohamed Maouche

We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results.

Design Choices for X-vector Based Speaker Anonymization

no code implementations • 18 May 2020 • Brij Mohan Lal Srivastava, Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Junichi Yamagishi, Mohamed Maouche, Aurélien Bellet, Marc Tommasi

The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker.

Speaker Verification