Membership Inference Attack Against Principal Component Analysis - 3IA Côte d’Azur – Interdisciplinary Institute for Artificial Intelligence Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Membership Inference Attack Against Principal Component Analysis

Résumé

This paper studies the performance of membership inference attacks against principal component analysis (PCA). In this attack, we assume that the adversary has access to the principal components, and her main goal is to infer whether a given data sample was used to compute these principal components. We show that our attack is successful and achieves high performance when the number of samples used to compute the principal components is small. As a defense strategy, we investigate the use of various differentially private mechanisms. Accordingly, we present experimental results on the performance of Gaussian and Laplace mechanisms under naive and advanced compositions against MIA as well as the utility of these differentially-private PCA solutions.
Fichier principal
Vignette du fichier
publi-7041.pdf (528.73 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03779050 , version 1 (16-09-2022)

Identifiants

Citer

Oualid Zari, Javier Parra-Arnau, Ayşe Ünsal, Thorsten Strufe, Melek Önen. Membership Inference Attack Against Principal Component Analysis. PSD 2022, Privacy in Statistical Databases, Sep 2022, Paris, France. pp.269-282, ⟨10.1007/978-3-031-13945-1_19⟩. ⟨hal-03779050⟩
41 Consultations
65 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More