Task-aware Privacy Preservation for Multi-dimensional Data

TL;DR

This paper proposes a task-aware privacy preservation method for multi-dimensional data using an encoder-decoder framework, significantly enhancing task performance under local differential privacy constraints.

Contribution

It introduces a novel task-aware approach with analytical and gradient-based solutions, improving utility in privacy-preserving data sharing for machine learning tasks.

Findings

Significant improvement in task accuracy over standard LDP methods.

Analytical near-optimal solution for linear cases.

Effective approximate solution for nonlinear cases.

Abstract

Local differential privacy (LDP) can be adopted to anonymize richer user data attributes that will be input to sophisticated machine learning (ML) tasks. However, today's LDP approaches are largely task-agnostic and often lead to severe performance loss -- they simply inject noise to all data attributes according to a given privacy budget, regardless of what features are most relevant for the ultimate task. In this paper, we address how to significantly improve the ultimate task performance with multi-dimensional user data by considering a task-aware privacy preservation problem. The key idea is to use an encoder-decoder framework to learn (and anonymize) a task-relevant latent representation of user data. We obtain an analytical near-optimal solution for the linear setting with mean-squared error (MSE) task loss. We also provide an approximate solution through a gradient-based learning algorithm for general nonlinear cases. Extensive experiments demonstrate that our task-aware approach significantly improves ultimate task accuracy compared to standard benchmark LDP approaches with the same level of privacy guarantee.