Scholar
Mohamed Maouche
Google Scholar ID: 7jBklWgAAAAJ
Inria
Citations & Impact
Citations
488
H-index
9
i10-index
9
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- - GRANITE: a Byzantine-Resilient Dynamic Gossip Learning Framework. (Preprint)
- - Secure Federated Graph-Filtering for Recommender Systems. (Preprint)
- - Differentially Private and Decentralized Randomized Power Method. (Preprint)
- - Inferring Communities of Interest in Collaborative Learning-based Recommender Systems. (ICDCS 25)
- - Scrutinizing the Vulnerability of Decentralized Learning to Membership Inference Attacks. (Preprint)
- - Synthetic Data: Generate Avatar Data on Demand. (WISE 24)
- - Towards an evolution in the characterization of the risk of re-identification of medical images. (Big Data 23)
- - Enhancing Speech Privacy with Slicing. (INTERSPEECH 22)
- - Privacy and utility of x-vector based speaker anonymization. (Transactions on Audio, Speech and Language Processing 2022)
- - Differentially Private Speaker Anonymization. (PETS 2023)
- - The VoicePrivacy 2020 Challenge: Results and findings. (Co)
Research Experience
- - Research Scientist, Inria, Privatics Team, 2022 - present.
- - Post-doc, Inria, DSVD Chaire, 2021 - 2022, working on privacy preserving federated learning alongside Sonia Ben Mokhtar, Antoine Boutet, and Jérémie Decouchant, focusing on health data in the context of car fleets.
- - Teacher, Université de Lille, 2021, teaching Dimension Reduction for the 1st year students of the machine learning master.
- - Post-doc, Inria, Magnet Team, 2019 - 2021, working on private machine learning for speech processing alongside Aurélien Bellet, Marc Tommasi, and Emmanuel Vincent.
- - Teacher, INSA-Lyon, 2016 - 2019, teaching computer science in the computer science department of INSA-Lyon (Dept. IF) and in the first cycle department (Dept PC).
Education
- - PhD, INSA-Lyon, LIRIS Lab, 2016-2019, in the fields of Data Science, Security and Privacy, focusing on Location Privacy and more precisely on re-identification attacks and obfuscation techniques.
- - Research Intern, Université de Technologie de Compiègne (UTC), Heudiasyc Lab, January 2016 - June 2016, in the field of Optimization in Operations research, working on the Vehicle Routing Problem (VRP) and the Robust VRP with Time windows constraints.
Background
- Main interest: Building machine learning systems that manage a good trade-off between privacy and utility. Exploring anonymization techniques and re-identification threats on different data types and applications.