Skip to Main content Skip to Navigation
Conference papers

Learning Semi-Supervised Anonymized Representations by Mutual Information

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.
Complete list of metadatas

https://hal-centralesupelec.archives-ouvertes.fr/hal-02572273
Contributor : Pierre Duhamel <>
Submitted on : Wednesday, May 13, 2020 - 3:39:30 PM
Last modification on : Saturday, October 3, 2020 - 4:16:26 AM

File

ICASSP.pdf
Files produced by the author(s)

Identifiers

Citation

C. Feutry, P. Piantanida, Pierre Duhamel. Learning Semi-Supervised Anonymized Representations by Mutual Information. 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), May 2020, Barcelone, Spain. pp.3467-3471, ⟨10.1109/ICASSP40776.2020.9053379⟩. ⟨hal-02572273⟩

Share

Metrics

Record views

28

Files downloads

79