Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary

TL;DR

This paper develops an online data release strategy balancing privacy and utility by modeling user data as correlated variables and using deep reinforcement learning to optimize information disclosure against a hypothesis testing adversary.

Contribution

It introduces a novel active sequential data release framework using MDPs and deep RL to manage privacy-utility trade-offs in real-time.

Findings

Effective privacy-utility trade-off achieved through deep RL methods.

Demonstrated the approach's ability to control information leakage.

Applicable to real-time privacy-preserving data sharing scenarios.

Abstract

We consider a user releasing her data containing some personal information in return of a service. We model user's personal information as two correlated random variables, one of them, called the secret variable, is to be kept private, while the other, called the useful variable, is to be disclosed for utility. We consider active sequential data release, where at each time step the user chooses from among a finite set of release mechanisms, each revealing some information about the user's personal information, i.e., the true hypotheses, albeit with different statistics. The user manages data release in an online fashion such that maximum amount of information is revealed about the latent useful variable, while the confidence for the sensitive variable is kept below a predefined level. For the utility, we consider both the probability of correct detection of the useful variable and the mutual information (MI) between the useful variable and released data. We formulate both problems as a Markov decision process (MDP), and numerically solve them by advantage actor-critic (A2C) deep reinforcement learning (RL).