Learning Anonymized Representations with Adversarial Neural Networks

By Clément Feutry, Pablo Piantanida, Yoshua Bengio, Pierre Duhamel. 2018

61 citations recorded by the source corpus.

Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. This paper investigates anonymization methods based on representation learning and deep neural networks, and motivated by novel information theoretical bounds. We introduce a novel training objective for simultaneously training a predictor over target variables of interest (the regular labels) while preventing an intermediate representation to be predictive of the private labels. The architecture is based on three sub-networks: one going from input to representation, one from representation to predicted regular labels, and one from representation to predicted private labels. The training procedure aims at learning representations that preserve the relevant part of the information (about regular labels) while dismissing information about the private labels which correspond to the identity of a person. We demonstrate the success of this approach for two distinct classification versus anonymization tasks (handwritten digits and sentiment analysis).

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Representation & Self-Supervised Learning

In Privacy & Security

Citations in the corpus

Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion? (2019, positive): “Inspired by [26], we further propose to extend the network with a speaker-adversarial branch so as to learn representations that perform well in ASR while hiding the speaker identity.”
Adversarial Removal of Demographic Attributes from Text Data (2018, methodology): “Adversarial training was also applied for Image anonymization (Edwards and Storkey, 2015; Feutry et al., 2018).”
Image-to-image translation for cross-domain disentanglement (2018, background): “A possible solution for this consists in bounding the loss by the performance of random chance [14].”
DeepObfuscator: Adversarial Training Framework for Privacy-Preserving Image Classification (2019, background): “Feutry et al. (Feutry et al. 2018) also propose an image anonymization approach to hide sensitive features related to private attributes.”
Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network (2019, unknown): “Ensemble Multi-feature [53] 97% Adversarial NN [54] 98.”