Scalable Privacy-Preserving Distributed Learning

Scalable Privacy-Preserving Distributed Learning

In this paper, we address the problem of privacy-preserving distributed learning and the evaluation of machine-learning models by analyzing it in the widespread MapReduce abstraction that we extend with privacy constraints. We design spindle (Scalable Privacy-preservINg Distributed LEarning), the fi...

Full description

Bibliographic Details
Main Authors: Froelicher David, Troncoso-Pastoriza Juan R., Pyrgelis Apostolos, Sav Sinem, Sousa Joao Sa, Bossuat Jean-Philippe, Hubaux Jean-Pierre
Format: Article
Language:English
Published: Sciendo 2021-04-01
Series:Proceedings on Privacy Enhancing Technologies
Subjects:
federated learning
multiparty homomorphic encryption
decentralized system
generalized linear models
Online Access:https://doi.org/10.2478/popets-2021-0030

Internet

https://doi.org/10.2478/popets-2021-0030

Similar Items