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

2025-06-11

AI Summary

In federated learning, anomalous or malicious clients—caused by sensor failures or non-IID data distributions—severely degrade global model performance; however, offline detection is highly challenging due to inaccessibility of raw client data. This paper proposes WAFFLE, the first framework enabling *pre-training offline anomaly detection*: it extracts compact, task-agnostic, non-invertible, and deformation-stable local representations via Wavelet Scattering Transform (WST) or Fourier Transform; then applies unsupervised embedding clustering coupled with a lightweight distilled detector—requiring neither raw data nor model updates. WST-based representations significantly enhance robustness and privacy compliance. Extensive experiments across multiple benchmark datasets demonstrate that WAFFLE substantially outperforms state-of-the-art online detection methods, achieving higher malicious-client identification accuracy and superior downstream classification performance.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Detect malicious clients in Federated Learning before training
• Use compressed representations from Wavelet or Fourier transforms
• Improve detection accuracy and classification performance in FL

Innovation

• Wavelet Scattering Transform for client detection
• Fourier Transform for low-dimensional embeddings
• Lightweight detector with minimal overhead