Designing a data sharing mechanism without sacrificing too much privacy can be considered as a game between data holders and malicious attackers. This paper describes a compressive adversarial privacy framework that captures the trade-off between the data privacy and utility. We characterize the optimal data releasing mechanism through convex optimization when assuming that both the data holder and attacker can only modify the data using linear transformations. We then build a more realistic data releasing mechanism that can rely on a nonlinear compression model while the attacker uses a neural network. We demonstrate in a series of empirical applications that this framework, consisting of compressive adversarial privacy, can preserve sensitive information.
@article{arxiv.1809.08911,
title = {Understanding Compressive Adversarial Privacy},
author = {Xiao Chen and Peter Kairouz and Ram Rajagopal},
journal= {arXiv preprint arXiv:1809.08911},
year = {2019}
}