Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval

Abstract

We consider the problem of information retrieval from a dataset of files stored on a single server under both a user distortion and a user privacy constraint. Specifically, a user requesting a file from the dataset should be able to reconstruct the requested file with a prescribed distortion, and in addition, the identity of the requested file should be kept private from the server with a prescribed privacy level. The proposed model can be seen as an extension of the well-known concept of private information retrieval by allowing for distortion in the retrieval process and relaxing the perfect privacy requirement. We initiate the study of the tradeoff between download rate, distortion, and user privacy leakage, and show that the optimal rate-distortion-leakage tradeoff is convex and that in the limit of large file sizes this allows for a concise information-theoretical formulation in terms of mutual information. Moreover, we propose a new data-driven framework by leveraging recent advancements in generative adversarial models which allows a user to learn efficient schemes in terms of download rate from the data itself. Learning the scheme is formulated as a constrained minimax game between a user which desires to keep the identity of the requested file private and an adversary that tries to infer which file the user is interested in under a distortion constraint. In general, guaranteeing a certain privacy level leads to a higher rate-distortion tradeoff curve, and hence a sacrifice in either download rate or distortion. We evaluate the performance of the scheme on a synthetic Gaussian dataset as well as on the MNIST and CIFAR-10 datasets. For the MNIST dataset, the data-driven approach significantly outperforms a proposed general achievable scheme combining source coding with the download of multiple files, while for CIFAR-10 the performances are comparable.

Optimal Rate-Distortion-Leakage Tradeoff for Single-Server Information Retrieval

“…To prove the converse part to Theorem 2, we first note that it was already shown in the converse proof of [28,Thm. 1] (see [28,…”

“…A similar setup to the one in this paper was considered in our companion paper [28]. However, in [28] the focus was on real-world datasets and on learning efficient schemes through a generative adversarial approach.…”

“…A similar setup to the one in this paper was considered in our companion paper [28]. However, in [28] the focus was on real-world datasets and on learning efficient schemes through a generative adversarial approach. This is in contrast to the current work which considers the case of independent and identically distributed (i.i.d.)…”