Image de couverture de livre

Sparsity in neural networks can improve their privacy

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gonon, Antoine, Zheng, Léon, Lalanne, Clément, Le, Quoc-Tung, Lauga, Guillaume, Pouliquen, Can
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Artificial Intelligence Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

_version_	1866917690305675264
author	Gonon, Antoine Zheng, Léon Lalanne, Clément Le, Quoc-Tung Lauga, Guillaume Pouliquen, Can
author_facet	Gonon, Antoine Zheng, Léon Lalanne, Clément Le, Quoc-Tung Lauga, Guillaume Pouliquen, Can
contents	This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of the network, while preserving comparable performances on the task at hand. This empirical study completes and extends existing literature.
format	Preprint
id	arxiv_https___arxiv_org_abs_2304_10553
institution	arXiv
publishDate	2023
record_format	arxiv
spellingShingle	Sparsity in neural networks can improve their privacy Gonon, Antoine Zheng, Léon Lalanne, Clément Le, Quoc-Tung Lauga, Guillaume Pouliquen, Can Machine Learning Artificial Intelligence Cryptography and Security This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of the network, while preserving comparable performances on the task at hand. This empirical study completes and extends existing literature.
title	Sparsity in neural networks can improve their privacy
topic	Machine Learning Artificial Intelligence Cryptography and Security
url	https://arxiv.org/abs/2304.10553