A Decentralized and Robust Protocol for ...
Type de document :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Titre :
A Decentralized and Robust Protocol for Private Averaging over Highly Distributed Data
Auteur(s) :
Dellenbach, Pierre [Auteur]
Machine Learning in Information Networks [MAGNET]
Ramon, Jan [Auteur]
Machine Learning in Information Networks [MAGNET]
Bellet, Aurelien [Auteur]
Machine Learning in Information Networks [MAGNET]
Machine Learning in Information Networks [MAGNET]
Ramon, Jan [Auteur]
Machine Learning in Information Networks [MAGNET]
Bellet, Aurelien [Auteur]
Machine Learning in Information Networks [MAGNET]
Titre de la manifestation scientifique :
NIPS 2016 workshop on Private Multi-Party Machine Learning
Ville :
Barcelone
Pays :
Espagne
Date de début de la manifestation scientifique :
2016-12-09
Discipline(s) HAL :
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Machine Learning [stat.ML]
Statistiques [stat]/Machine Learning [stat.ML]
Résumé en anglais : [en]
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, ...
Lire la suite >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.Lire moins >
Lire la suite >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.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :