A Decentralized and Robust Protocol for Private Averaging over Highly Distributed Data

Pierre Dellenbach 1 Jan Ramon 1 Aurélien Bellet 1
1 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : We propose a decentralized protocol for a large set of users to privately compute averages over their joint data, which can later be used to learn more complex models. Our protocol can find a solution of arbitrary accuracy, does not rely on a trusted third party and preserves the privacy of users throughout the execution in both the honest-but-curious and malicious adversary models. Furthermore, we design a verification procedure which offers protection against malicious users joining the service with the goal of manipulating the outcome of the algorithm.
Type de document :
Poster
NIPS 2016 workshop on Private Multi-Party Machine Learning, Dec 2016, Barcelone, Spain. 〈https://pmpml.github.io/PMPML16/〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01384148
Contributeur : Aurélien Bellet <>
Soumis le : mercredi 19 octobre 2016 - 14:30:34
Dernière modification le : mardi 3 juillet 2018 - 11:27:24

Identifiants

  • HAL Id : hal-01384148, version 1

Citation

Pierre Dellenbach, Jan Ramon, Aurélien Bellet. A Decentralized and Robust Protocol for Private Averaging over Highly Distributed Data. NIPS 2016 workshop on Private Multi-Party Machine Learning, Dec 2016, Barcelone, Spain. 〈https://pmpml.github.io/PMPML16/〉. 〈hal-01384148〉

Partager

Métriques

Consultations de la notice

450