Federated Learning Nodes Can Reconstruct Peers' Image Data

TL;DR

This paper reveals that in federated learning, individual nodes can secretly reconstruct other nodes' private image data using gradient inversion and diffusion models, exposing significant privacy vulnerabilities.

Contribution

It demonstrates that honest-but-curious clients can perform silent, high-quality image reconstruction attacks on peers using gradient information and diffusion models, highlighting privacy risks.

Findings

Single clients can reconstruct peers' images from updates.

Diffusion models improve the perceptual quality of reconstructed images.

Reveals severe privacy risks in federated learning environments.

Abstract

Federated learning (FL) is a privacy-preserving machine learning framework that enables multiple nodes to train models on their local data and periodically average weight updates to benefit from other nodes' training. Each node's goal is to collaborate with other nodes to improve the model's performance while keeping its training data private. However, this framework does not guarantee data privacy. Prior work has shown that the gradient-sharing steps in FL can be vulnerable to data reconstruction attacks from an honest-but-curious central server. In this work, we show that an honest-but-curious node/client can also launch attacks to reconstruct peers' image data through gradient inversion, presenting a severe privacy risk. We demonstrate that a single client can silently reconstruct other clients' private images using diluted information available within consecutive updates. We leverage state-of-the-art diffusion models to enhance the perceptual quality and recognizability of the reconstructed images, further demonstrating the risk of information leakage at a semantic level. This highlights the need for more robust privacy-preserving mechanisms that protect against silent client-side attacks during federated training.