Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks

TL;DR

Fed-Listing introduces a gradient-based attack that infers private label distributions in federated GNNs, exposing privacy vulnerabilities even with existing defenses and without access to raw data.

Contribution

This work presents Fed-Listing, a novel method for inferring clients' label distributions in FedGNNs using only final-layer gradients, highlighting privacy risks.

Findings

Fed-Listing outperforms existing baselines in experiments.

It effectively infers label distributions under non-i.i.d. scenarios.

Existing defenses are largely ineffective against Fed-Listing.

Abstract

Federated Graph Neural Networks (FedGNNs) facilitate collaborative learning across multiple clients with graph-structured data while preserving user privacy. However, emerging research indicates that within this setting, shared model updates, particularly gradients, can unintentionally leak sensitive information of local users. Numerous privacy inference attacks have been explored in traditional federated learning and extended to graph settings, but the problem of label distribution inference in FedGNNs remains largely underexplored. In this work, we introduce Fed-Listing (Federated Label Distribution Inference in GNNs), a novel gradient-based attack designed to infer the private label statistics of target clients in FedGNNs without access to raw data or node features. Fed-Listing only leverages the final-layer gradients exchanged during training to uncover statistical patterns that reveal class proportions in a stealthy manner. Extensive experiments on four benchmark datasets and three GNN architectures show that Fed-Listing significantly outperforms existing baselines, including random guessing and Decaf, even under challenging non-i.i.d. scenarios. Moreover, existing defense mechanisms can barely reduce the attack performance of Fed-Listing, unless the model's utility is severely degraded. The code implementation and Supplementary materials are available here: https://github.com/suprimnakarmi/Fed-Listing.