GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models

TL;DR

This paper introduces GUIDE, a novel method using diffusion-based denoising models to significantly improve image reconstruction attacks in federated learning, revealing privacy vulnerabilities.

Contribution

GUIDE is the first approach to incorporate diffusion models for enhancing gradient inversion attacks in federated learning, improving reconstruction quality.

Findings

GUIDE improves image reconstruction quality by up to 46% in perceptual similarity.

The method seamlessly integrates with existing gradient inversion attacks.

GUIDE demonstrates effectiveness across different FL algorithms, models, and datasets.

Abstract

Federated Learning (FL) enables collaborative training of Machine Learning (ML) models across multiple clients while preserving their privacy. Rather than sharing raw data, federated clients transmit locally computed updates to train the global model. Although this paradigm should provide stronger privacy guarantees than centralized ML, client updates remain vulnerable to privacy leakage. Adversaries can exploit them to infer sensitive properties about the training data or even to reconstruct the original inputs via Gradient Inversion Attacks (GIAs). Under the honest-butcurious threat model, GIAs attempt to reconstruct training data by reversing intermediate updates using optimizationbased techniques. We observe that these approaches usually reconstruct noisy approximations of the original inputs, whose quality can be enhanced with specialized denoising models. This paper presents Gradient Update Inversion with DEnoising (GUIDE), a novel methodology that leverages diffusion models as denoising tools to improve image reconstruction attacks in FL. GUIDE can be integrated into any GIAs that exploits surrogate datasets, a widely adopted assumption in GIAs literature. We comprehensively evaluate our approach in two attack scenarios that use different FL algorithms, models, and datasets. Our results demonstrate that GUIDE integrates seamlessly with two state-ofthe- art GIAs, substantially improving reconstruction quality across multiple metrics. Specifically, GUIDE achieves up to 46% higher perceptual similarity, as measured by the DreamSim metric.