Attribute Inference Attacks for Federated Regression Tasks

TL;DR

This paper introduces novel attribute inference attacks tailored for federated regression tasks, revealing significant privacy risks and outperforming existing methods in real-world scenarios.

Contribution

It develops model-based AIAs specifically for federated regression, addressing a gap in understanding privacy leakage in this context.

Findings

Significant increase in reconstruction accuracy, especially in heterogeneous datasets.

Model-based AIAs outperform state-of-the-art methods.

Effective in scenarios with message eavesdropping or direct interference.

Abstract

Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine learning model while keeping their data localized. However, recent studies have revealed that the training phase of FL is vulnerable to reconstruction attacks, such as attribute inference attacks (AIA), where adversaries exploit exchanged messages and auxiliary public information to uncover sensitive attributes of targeted clients. While these attacks have been extensively studied in the context of classification tasks, their impact on regression tasks remains largely unexplored. In this paper, we address this gap by proposing novel model-based AIAs specifically designed for regression tasks in FL environments. Our approach considers scenarios where adversaries can either eavesdrop on exchanged messages or directly interfere with the training process. We benchmark our proposed attacks against state-of-the-art methods using real-world datasets. The results demonstrate a significant increase in reconstruction accuracy, particularly in heterogeneous client datasets, a common scenario in FL. The efficacy of our model-based AIAs makes them better candidates for empirically quantifying privacy leakage for federated regression tasks.