Learning Semi-Supervised Anonymized Representations by Mutual Information - CentraleSupélec Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Learning Semi-Supervised Anonymized Representations by Mutual Information

Résumé

This paper addresses the problem of removing from a set of data (here images) a given private information, while still allowing other utilities on the processed data. This is obtained by training concurrently a GAN-like discriminator and an autoencoder. The optimization of the resulting structure involves a novel surrogate of the misclassification probability of the information to remove. Several examples are given, demonstrating that a good level of privacy can be obtained on images at the cost of the introduction of very small artifacts.
Fichier principal
Vignette du fichier
LEARNING SEMI-SUPERVISED ANONYMIZED REPRESENTATIONS BY MUTUAL INFORMATION (1).pdf (1.32 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03351090 , version 1 (21-09-2021)
hal-03351090 , version 2 (19-01-2022)
hal-03351090 , version 3 (22-06-2023)

Licence

Domaine public

Identifiants

Citer

Clément Feutry, Pablo Piantanida, Pierre Duhamel. Learning Semi-Supervised Anonymized Representations by Mutual Information. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, Barcelona, Spain, France. pp.3467-3471, ⟨10.1109/ICASSP40776.2020.9053379⟩. ⟨hal-03351090v3⟩
52 Consultations
84 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More