Support Vector Based Anomaly Detection in Federated Learning

TL;DR

This paper presents two novel Support Vector Machine-based algorithms for anomaly detection in federated learning, addressing privacy concerns and computational efficiency, with promising initial results in distributed systems.

Contribution

Introduction of Ensemble SVDD and Support Vector Election algorithms for anomaly detection in federated learning, offering effective performance with small datasets and lower computational costs.

Findings

Algorithms perform well in distributed configurations

Potential for privacy-preserving anomaly detection

Lower computational costs compared to neural networks

Abstract

Anomaly detection plays a crucial role in various domains, from cybersecurity to industrial systems. However, traditional centralized approaches often encounter challenges related to data privacy. In this context, Federated Learning emerges as a promising solution. This work introduces two innovative algorithms--Ensemble SVDD and Support Vector Election--that leverage Support Vector Machines for anomaly detection in a federated setting. In comparison with the Neural Networks typically used in within Federated Learning, these new algorithms emerge as potential alternatives, as they can operate effectively with small datasets and incur lower computational costs. The novel algorithms are tested in various distributed system configurations, yielding promising initial results that pave the way for further investigation.