MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2021

MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers

Abstract

Machine Learning (ML) has emerged as a core technology to provide learning models to perform complex tasks. Boosted by Machine Learning as a Service (MLaaS), the number of applications relying on ML capabilities is ever increasing. However, ML models are the source of different privacy violations through passive or active attacks from different entities. In this paper, we present MixNN a proxy-based privacy-preserving system for federated learning to protect the privacy of participants against a curious or malicious aggregation server trying to infer sensitive information (i.e., membership and attribute inferences). MixNN receives the model updates from participants and mixes layers between participants before sending the mixed updates to the aggregation server. This mixing strategy drastically reduces privacy leaks without any trade-off with utility. Indeed, mixing the updates of the model has no impact on the result of the aggregation of the updates computed by the server. We report on an extensive evaluation of MixNN using several datasets and neural networks architectures to quantify privacy leakage through membership and attribute inference attacks as well the robustness of the protection. We show that MixNN significantly limits both the membership and attribute inferences compared to a baseline using model compression and noisy gradient (well known to damage the utility) while keeping the same level of utility as classic federated learning.
Fichier principal
Vignette du fichier
MixNN (19).pdf (1.82 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03354724 , version 1 (26-09-2021)

Identifiers

  • HAL Id : hal-03354724 , version 1

Cite

Antoine Boutet, Thomas Lebrun, Jan Aalmoes, Adrien Baud. MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers. [Research Report] RR-9411, INRIA Grenoble. 2021, pp.1-21. ⟨hal-03354724⟩
86 View
135 Download

Share

Gmail Mastodon Facebook X LinkedIn More