English

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

Cryptography and Security 2022-01-25 v2 Audio and Speech Processing

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.

Keywords

Cite

@article{arxiv.2110.05840,
  title  = {A bridge between features and evidence for binary attribute-driven perfect privacy},
  author = {Paul-Gauthier Noé and Andreas Nautsch and Driss Matrouf and Pierre-Michel Bousquet and Jean-François Bonastre},
  journal= {arXiv preprint arXiv:2110.05840},
  year   = {2022}
}

Comments

ICASSP 2022

R2 v1 2026-06-24T06:49:07.577Z