Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

Privacy Amplification by Decentralization

Edwige Cyffers 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 - UMR 9189
Abstract : Analyzing data owned by several parties while achieving a good trade-off between utility and privacy is a key challenge in federated learning and analytics. In this work, we introduce a novel relaxation of local differential privacy (LDP) that naturally arises in fully decentralized algorithms, i.e., when participants exchange information by communicating along the edges of a network graph without central coordinator. This relaxation, that we call network DP, captures the fact that users have only a local view of the system. To show the relevance of network DP, we study a decentralized model of computation where a token performs a walk on the network graph and is updated sequentially by the party who receives it. For tasks such as real summation, histogram computation and optimization with gradient descent, we propose simple algorithms on ring and complete topologies. We prove that the privacy-utility trade-offs of our algorithms under network DP significantly improve upon what is achievable under LDP (sometimes even matching the utility of the trusted curator model), showing for the first time that formal privacy gains can be obtained from full decentralization. Our experiments illustrate the improved utility of our approach for decentralized training with stochastic gradient descent.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Aurélien Bellet Connect in order to contact the contributor
Submitted on : Wednesday, November 17, 2021 - 6:53:14 PM
Last modification on : Tuesday, November 22, 2022 - 2:26:16 PM


Files produced by the author(s)


  • HAL Id : hal-03100005, version 3
  • ARXIV : 2012.05326


Edwige Cyffers, Aurélien Bellet. Privacy Amplification by Decentralization. 2020. ⟨hal-03100005v3⟩



Record views


Files downloads