FedGIG: Graph Inversion from Gradient in Federated Learning

TL;DR

This paper introduces FedGIG, a novel gradient inversion attack tailored for federated graph learning, capable of reconstructing sparse, discrete graph data with high accuracy, highlighting privacy vulnerabilities.

Contribution

FedGIG is the first GIA method specifically designed for graph-structured data, incorporating modules to ensure sparsity and reconstruct missing subgraphs in federated settings.

Findings

FedGIG outperforms existing GIA methods on molecular datasets.

It effectively reconstructs sparse, discrete graph data.

Demonstrates privacy risks in federated graph learning environments.

Abstract

Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, continuous data such as images or vectorized texts, and cannot be directly applied to sparse and discrete graph data. This paper first explores GIA's impact on Federated Graph Learning (FGL) and introduces Graph Inversion from Gradient in Federated Learning (FedGIG), a novel GIA method specifically designed for graph-structured data. FedGIG includes the adjacency matrix constraining module, which ensures the sparsity and discreteness of the reconstructed graph data, and the subgraph reconstruction module, which is designed to complete missing common subgraph structures. Extensive experiments on molecular datasets demonstrate FedGIG's superior accuracy over existing GIA techniques.