Localisation

Adresses

Aix-Marseille Université
Institut de Mathématiques de Marseille (I2M) - UMR 7373
Site Saint-Charles : 3 place Victor Hugo, Case 19, 13331 Marseille Cedex 3
Site Luminy : Campus de Luminy - Case 907 - 13288 Marseille Cedex 9

Séminaire

Privacy-Preserving Federated Learning

Aurélien BELLET
INRIA Lille
http://researchers.lille.inria.fr/abellet/

Date(s) : 25/03/2022   iCal
14h30 - 15h30

Federated learning (FL) is a machine learning paradigm where several participants collaboratively train a model while keeping their data decentralized. However, the model parameters or gradients exchanged during the FL training process may leak information about the data. After a brief introduction to FL, I will show how to use the notion of Differential Privacy (DP) to design FL algorithms that provably ensure privacy and confidentiality. In particular, I will present two approaches (one for server-orchestrated FL and one for fully decentralized FL) that nearly match the privacy-utility trade-off of the centralized setting without relying on a trusted curator or complex secure computation primitives.

 

Catégories


Secured By miniOrange