Learning Semi-Supervised Anonymized Representations by Mutual Information - Archive ouverte HAL Access content directly
Conference Papers Year :

Learning Semi-Supervised Anonymized Representations by Mutual Information

(1) , (2, 1) , (1)
1
2

Abstract

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
Template.pdf (786.14 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03351090 , version 1 (21-09-2021)
hal-03351090 , version 2 (19-01-2022)

Licence

Public Domain

Identifiers

Cite

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-03351090v2⟩
30 View
43 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More