Network Anomaly Traffic Detection via Multi-view Feature Fusion

TL;DR

This paper introduces MuFF, a multi-view feature fusion method that combines temporal and interactive features for improved network anomaly traffic detection, outperforming single-view approaches.

Contribution

The paper presents a novel multi-view feature fusion approach that models both temporal and interactive relationships in network traffic for enhanced anomaly detection.

Findings

MuFF outperforms traditional single-view methods in experiments.

It effectively captures complex attack patterns and encrypted traffic.

Extensive tests on six datasets validate its robustness.

Abstract

Traditional anomalous traffic detection methods are based on single-view analysis, which has obvious limitations in dealing with complex attacks and encrypted communications. In this regard, we propose a Multi-view Feature Fusion (MuFF) method for network anomaly traffic detection. MuFF models the temporal and interactive relationships of packets in network traffic based on the temporal and interactive viewpoints respectively. It learns temporal and interactive features. These features are then fused from different perspectives for anomaly traffic detection. Extensive experiments on six real traffic datasets show that MuFF has excellent performance in network anomalous traffic detection, which makes up for the shortcomings of detection under a single perspective.