A bridge between features and evidence for binary attribute-driven perfect privacy

TL;DR

This paper introduces a normalizing flow-based method to achieve perfect privacy by disentangling and manipulating features related to binary attributes, demonstrated on speaker embeddings to hide sex information.

Contribution

It proposes a novel invertible mapping approach for attribute-driven privacy that outperforms previous adversarial methods in privacy and utility.

Findings

Effective removal of sex information from speaker embeddings

Outperforms previous adversarial disentanglement methods

Maintains utility while ensuring perfect privacy

Abstract

Attribute-driven privacy aims to conceal a single user's attribute, contrary to anonymisation that tries to hide the full identity of the user in some data. When the attribute to protect from malicious inferences is binary, perfect privacy requires the log-likelihood-ratio to be zero resulting in no strength-of-evidence. This work presents an approach based on normalizing flow that maps a feature vector into a latent space where the evidence, related to the binary attribute, and an independent residual are disentangled. It can be seen as a non-linear discriminant analysis where the mapping is invertible allowing generation by mapping the latent variable back to the original space. This framework allows to manipulate the log-likelihood-ratio of the data and therefore allows to set it to zero for privacy. We show the applicability of the approach on an attribute-driven privacy task where the sex information is removed from speaker embeddings. Results on VoxCeleb2 dataset show the efficiency of the method that outperforms in terms of privacy and utility our previous experiments based on adversarial disentanglement.