ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generation

TL;DR

This paper introduces ST-DPGAN, a novel Graph-GAN framework that generates privacy-preserving spatiotemporal data with differential privacy guarantees, enabling secure data sharing without compromising utility.

Contribution

The paper presents a new Graph-GAN model with spatial-temporal attention and deconvolution structures that ensures differential privacy in spatiotemporal data generation.

Findings

Effective privacy protection demonstrated on real datasets

Maintains high data utility comparable to original data

Model training on generated data yields competitive results

Abstract

Spatiotemporal data is prevalent in a wide range of edge devices, such as those used in personal communication and financial transactions. Recent advancements have sparked a growing interest in integrating spatiotemporal analysis with large-scale language models. However, spatiotemporal data often contains sensitive information, making it unsuitable for open third-party access. To address this challenge, we propose a Graph-GAN-based model for generating privacy-protected spatiotemporal data. Our approach incorporates spatial and temporal attention blocks in the discriminator and a spatiotemporal deconvolution structure in the generator. These enhancements enable efficient training under Gaussian noise to achieve differential privacy. Extensive experiments conducted on three real-world spatiotemporal datasets validate the efficacy of our model. Our method provides a privacy guarantee while maintaining the data utility. The prediction model trained on our generated data maintains a competitive performance compared to the model trained on the original data.