Skip to Main content Skip to Navigation
Poster communications

Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties

César Sabater 1 Aurélien Bellet 1 Jan Ramon 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 : Learning from data owned by several parties, as in federated learning, raises challenges regarding the privacy guarantees provided to participants and the correctness of the computation in the presence of malicious parties. We tackle these challenges in the context of distributed averaging, an essential building block of distributed and federated learning. Our first contribution is a novel distributed differentially private protocol which can match the accuracy of the trusted curator model even when each party communicates with only a logarithmic number of other parties chosen at random. Our second contribution is to enable users to prove the correctness of their computations without compromising the efficiency and privacy guarantees of the protocol. Our construction relies on standard cryptographic primitives like commitment schemes and zero knowledge proofs.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03117816
Contributor : César Sabater Connect in order to contact the contributor
Submitted on : Thursday, January 21, 2021 - 3:35:39 PM
Last modification on : Friday, January 21, 2022 - 3:12:50 AM

Links full text

Identifiers

  • HAL Id : hal-03117816, version 1
  • ARXIV : 2006.07218

Collections

Citation

César Sabater, Aurélien Bellet, Jan Ramon. Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties. NeurIPS 2020 workshop on Privacy Preserving Machine Learning - PriML and PPML Joint Edition, Dec 2020, Vancouver (Virtual Workshop), Canada. ⟨hal-03117816⟩

Share

Metrics

Les métriques sont temporairement indisponibles