Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval

arXiv2012.03902MaRDI QIDQ6355489

Author name not available (Why is that?)

Publication date: 7 December 2020

Abstract: We propose to extend the concept of private information retrieval by allowing for distortion in the retrieval process and relaxing the perfect privacy requirement at the same time. In particular, we study the trade-off between download rate, distortion, and user privacy leakage, and show that in the limit of large file sizes this trade-off can be captured via a novel information-theoretical formulation for datasets with a known distribution. Moreover, for scenarios where the statistics of the dataset is unknown, we propose a new deep learning framework by leveraging a generative adversarial network approach, which allows the user to learn efficient schemes from the data itself. We evaluate the performance of the scheme on a synthetic Gaussian dataset as well as on the MNIST, CIFAR-10, and LSUN datasets. For the MNIST, CIFAR-10, and LSUN datasets, the data-driven approach significantly outperforms a nonlearning-based scheme which combines source coding with the download of multiple files.

Has companion code repository: https://github.com/Simula-UiB/GAUP_TIFS22

This page was built for publication: Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6355489)