LGAICRSINov 17, 2021

Network Generation with Differential Privacy

arXiv:2111.09085v13 citations
Originality Incremental advance
AI Analysis

This work addresses privacy concerns for graph data in domains like social networks, though it is incremental as it builds on existing DP-SGD and GAN techniques.

The paper tackles the problem of generating synthetic graphs that preserve privacy while maintaining utility, by proposing a model that reproduces real-world network properties with edge-differential privacy, achieving results comparable to state-of-the-art methods on common datasets.

We consider the problem of generating private synthetic versions of real-world graphs containing private information while maintaining the utility of generated graphs. Differential privacy is a gold standard for data privacy, and the introduction of the differentially private stochastic gradient descent (DP-SGD) algorithm has facilitated the training of private neural models in a number of domains. Recent advances in graph generation via deep generative networks have produced several high performing models. We evaluate and compare state-of-the-art models including adjacency matrix based models and edge based models, and show a practical implementation that favours the edge-list approach utilizing the Gaussian noise mechanism when evaluated on commonly used graph datasets. Based on our findings, we propose a generative model that can reproduce the properties of real-world networks while maintaining edge-differential privacy. The proposed model is based on a stochastic neural network that generates discrete edge-list samples and is trained using the Wasserstein GAN objective with the DP-SGD optimizer. Being the first approach to combine these beneficial properties, our model contributes to further research on graph data privacy.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes