Application-driven Privacy-preserving Data Publishing with Correlated Attributes

TL;DR

This paper introduces PR-GAN, a privacy-preserving data publishing framework that uses generative adversarial networks to hide sensitive attributes while maintaining data utility, accounting for attribute correlations and providing privacy guarantees.

Contribution

The paper presents a novel GAN-based framework that automatically modifies data to hide sensitive attributes considering correlations, with formal privacy guarantees under the Pufferfish model.

Findings

PR-GAN effectively hides sensitive attributes in data.

It maintains high utility for target applications.

It generalizes well across different data groups.

Abstract

Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework called PR-GAN that offers privacy-preserving mechanism using generative adversarial networks. Given a target application, PR-GAN automatically modifies the data to hide sensitive attributes -- which may be hidden and can be inferred by machine learning algorithms -- while preserving the data utility in the target application. Unlike prior works, the public's possible knowledge of the correlation between the target application and sensitive attributes is built into our modeling. We formulate our problem as an optimization problem, show that an optimal solution exists and use generative adversarial networks (GAN) to create perturbations. We further show that our method provides privacy guarantees under the Pufferfish framework, an elegant generalization of the differential privacy that allows for the modeling of prior knowledge on data and correlations. Through experiments, we show that our method outperforms conventional methods in effectively hiding the sensitive attributes while guaranteeing high performance in the target application, for both property inference and training purposes. Finally, we demonstrate through further experiments that once our model learns a privacy-preserving task, such as hiding subjects' identity, on a group of individuals, it can perform the same task on a separate group with minimal performance drops.