Learning Semi-Supervised Anonymized Representations by Mutual Information

Clément Feutry; Pablo Piantanida; Pierre Duhamel

ICASSP 2020accepted0 citations

Learning Semi-Supervised Anonymized Representations by Mutual Information

Clément Feutry, Pablo Piantanida, Pierre Duhamel

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.

BibTeX

@inproceedings{icassp2020_learningsemisupe,
  title = {Learning Semi-Supervised Anonymized Representations by Mutual Information},
  author = {Clément Feutry and Pablo Piantanida and Pierre Duhamel},
  booktitle = {ICASSP 2020},
  year = {2020}
}