On the Usage of Generative Models for Network Anomaly Detection in Multivariate Time-Series

TL;DR

This paper introduces Net-GAN and Net-VAE, innovative generative model-based methods for detecting anomalies in multivariate network time-series data, addressing the limitations of univariate-focused approaches.

Contribution

The paper presents Net-GAN and Net-VAE, novel generative models that detect anomalies in multivariate time-series without prior assumptions, leveraging RNNs and VAEs respectively.

Findings

Effective in IoT sensor anomaly detection

Successful intrusion detection in network data

Outperforms traditional univariate methods

Abstract

Despite the many attempts and approaches for anomaly detection explored over the years, the automatic detection of rare events in data communication networks remains a complex problem. In this paper we introduce Net-GAN, a novel approach to network anomaly detection in time-series, using recurrent neural networks (RNNs) and generative adversarial networks (GAN). Different from the state of the art, which traditionally focuses on univariate measurements, Net-GAN detects anomalies in multivariate time-series, exploiting temporal dependencies through RNNs. Net-GAN discovers the underlying distribution of the baseline, multivariate data, without making any assumptions on its nature, offering a powerful approach to detect anomalies in complex, difficult to model network monitoring data. We further exploit the concepts behind generative models to conceive Net-VAE, a complementary approach to Net-GAN for network anomaly detection, based on variational auto-encoders (VAE). We evaluate Net-GAN and Net-VAE in different monitoring scenarios, including anomaly detection in IoT sensor data, and intrusion detection in network measurements. Generative models represent a promising approach for network anomaly detection, especially when considering the complexity and ever-growing number of time-series to monitor in operational networks.