Learning Semi-Supervised Anonymized Representations by Mutual Information

C. Feutry (1) , Pablo Piantanida (1) , Pierre Duhamel (1)

1 L2S - Laboratoire des signaux et systèmes

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.

Domains: Computer Science [cs]; Artificial Intelligence [cs.AI]; Computer Science [cs]; Information Theory [cs.IT]

C. Feutry, Pablo 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⟩