GNN-based Anomaly Detection for Encoded Network Traffic

TL;DR

This research investigates using Graph Neural Networks with enriched feature encoding to improve anomaly detection in network traffic data, addressing a gap in applying GNNs to network flow analysis.

Contribution

It introduces a novel approach combining feature encoding with GNNs for enhanced anomaly detection in network traffic data.

Findings

GNNs with feature encoding improve anomaly detection accuracy.

Enriched features capture complex relationships in network data.

Potential for better real-time network security monitoring.

Abstract

The early research report explores the possibility of using Graph Neural Networks (GNNs) for anomaly detection in internet traffic data enriched with information. While recent studies have made significant progress in using GNNs for anomaly detection in finance, multivariate time-series, and biochemistry domains, there is limited research in the context of network flow data. In this report, we explore the idea that leverages information-enriched features extracted from network flow packet data to improve the performance of GNN in anomaly detection. The idea is to utilize feature encoding (binary, numerical, and string) to capture the relationships between the network components, allowing the GNN to learn latent relationships and better identify anomalies.