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

by   Paul-Gauthier Noé, et al.

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 strength-of-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 thus 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.


page 1

page 2

page 3

page 4


Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation

With the increasing interest over speech technologies, numerous Automati...

Latent Space Factorisation and Manipulation via Matrix Subspace Projection

This paper proposes a novel method for factorising the information in th...

PassFlow: Guessing Passwords with Generative Flows

Recent advances in generative machine learning models rekindled research...

On Perfect Obfuscation: Local Information Geometry Analysis

We consider the problem of privacy-preserving data release for a specifi...

Multiobjective Optimization Training of PLDA for Speaker Verification

Most current state-of-the-art text-independent speaker verification syst...

Deep Log-Likelihood Ratio Quantization

In this work, a deep learning-based method for log-likelihood ratio (LLR...

Single-Component Privacy Guarantees in Helper Data Systems and Sparse Coding

We investigate the privacy of two approaches to (biometric) template pro...

Code Repositories