On the Usage of Generative Models for Network Anomaly Detection in Multivariate Time-Series
This work addresses the problem of detecting rare events in complex network monitoring data for network operators, representing an incremental advancement by applying existing generative models to a specific domain.
The paper tackles network anomaly detection in multivariate time-series by introducing Net-GAN and Net-VAE, which use generative models like GANs and VAEs to detect anomalies without assumptions on data distribution, achieving promising results in scenarios like IoT sensor data and intrusion detection.
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.