Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning

Abstract

Federated learning (FL) is a decentralized model training framework that aims to merge isolated data islands while maintaining data privacy. However, recent studies have revealed that Generative Adversarial Network (GAN) based attacks can be employed in FL to learn the distribution of private datasets and reconstruct recognizable images. In this paper, we exploit defenses against GAN-based attacks in FL and propose a framework, Anti-GAN, to prevent attackers from learning the real distribution of the victim's data. The core idea of Anti-GAN is to manipulate the visual features of private training images to make them indistinguishable to human eyes even restored by attackers. Specifically, Anti-GAN projects the private dataset onto a GAN's generator and combines the generated fake images with the actual images to create the training dataset, which is then used for federated model training. The experimental results demonstrate that Anti-GAN is effective in preventing attackers from learning the distribution of private images while causing minimal harm to the accuracy of the federated model.

Published in ACM Transactions on Knowledge Discovery from Data (TKDD), 2025

References in corpus (9)

• Deep Learning with Differential Privacy
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
• Feature Inference Attack on Model Predictions in Vertical Federated Learning
• Privacy Preserving Vertical Federated Learning for Tree-based Models
• Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
• Feature Inference Attack on Shapley Values
• Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective
• A Fusion-Denoising Attack on InstaHide with Data Augmentation