Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning

TL;DR

This paper introduces WAFFLE, a novel method for detecting malicious clients in federated learning using wavelet and Fourier transforms to create low-dimensional embeddings for unsupervised anomaly detection, improving accuracy and efficiency.

Contribution

The paper presents WAFFLE, a new detection algorithm leveraging wavelet scattering and Fourier transforms for pre-training anomaly detection in federated learning, with theoretical and empirical advantages.

Findings

WST-based embeddings are stable and non-invertible, aiding detection.

WAFFLE outperforms existing methods in detection accuracy.

The approach requires minimal communication and computation.

Abstract

Federated Learning (FL) enables the training of machine learning models across decentralized clients while preserving data privacy. However, the presence of anomalous or corrupted clients - such as those with faulty sensors or non representative data distributions - can significantly degrade model performance. Detecting such clients without accessing raw data remains a key challenge. We propose WAFFLE (Wavelet and Fourier representations for Federated Learning) a detection algorithm that labels malicious clients {\it before training}, using locally computed compressed representations derived from either the Wavelet Scattering Transform (WST) or the Fourier Transform. Both approaches provide low-dimensional, task-agnostic embeddings suitable for unsupervised client separation. A lightweight detector, trained on a distillated public dataset, performs the labeling with minimal communication and computational overhead. While both transforms enable effective detection, WST offers theoretical advantages, such as non-invertibility and stability to local deformations, that make it particularly well-suited to federated scenarios. Experiments on benchmark datasets show that our method improves detection accuracy and downstream classification performance compared to existing FL anomaly detection algorithms, validating its effectiveness as a pre-training alternative to online detection strategies.