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

Alessandro Licciardi, Davide Leo, Davide Carbone

Keywords: Federated Learning, Malicious Client Detection, Representation Operators

TL;DR: We propose a pre-training client anomaly detection method for Federated Learning using compressed signal representations and a lightweight external detector.

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** (**Wa**velet and **F**ourier representations for **F**ederated **Le**arning) a detection algorithm that labels malicious clients 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.

Primary Area: General machine learning (supervised, unsupervised, online, active, etc.)

Submission Number: 12703