MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks

Abstract

The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems. The rich sensor data can be continuously monitored for intrusion events through anomaly detection. However, conventional threshold-based anomaly detection methods are inadequate due to the dynamic complexities of these systems, while supervised machine learning methods are unable to exploit the large amounts of data due to the lack of labeled data. On the other hand, current unsupervised machine learning approaches have not fully exploited the spatial-temporal correlation and other dependencies amongst the multiple variables (sensors/actuators) in the system for detecting anomalies. In this work, we propose an unsupervised multivariate anomaly detection method based on Generative Adversarial Networks (GANs). Instead of treating each data stream independently, our proposed MAD-GAN framework considers the entire variable set concurrently to capture the latent interactions amongst the variables. We also fully exploit both the generator and discriminator produced by the GAN, using a novel anomaly score called DR-score to detect anomalies by discrimination and reconstruction. We have tested our proposed MAD-GAN using two recent datasets collected from real-world CPS: the Secure Water Treatment (SWaT) and the Water Distribution (WADI) datasets. Our experimental results showed that the proposed MAD-GAN is effective in reporting anomalies caused by various cyber-intrusions compared in these complex real-world systems.

This is a pre-print of an on-going work. arXiv admin note: text overlap with arXiv:1809.04758

References in corpus (2)

• Adversarial Feature Selection against Evasion Attacks
• Efficient augmentation and relaxation learning for individualized treatment rules using observational data

Cited by in corpus (14)

• An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Generative adversarial networks in time series: A survey and taxonomy
• Multivariate Time-series Anomaly Detection via Graph Attention Network
• Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
• A Time-Temperature Dataset for the Strawberry Cold Chain Across Multiple Shipments and Locations
• NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection
• Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Defending Water Treatment Networks: Exploiting Spatio-temporal Effects for Cyber Attack Detection
• Anomaly Detection and Sampling Cost Control via Hierarchical GANs
• Autoencoder-based Representation Learning from Heterogeneous Multivariate Time Series Data of Mechatronic Systems
• Generative Optimization Networks for Memory Efficient Data Generation
• Unsupervised Learning Based Robust Multivariate Intrusion Detection System for Cyber-Physical Systems using Low Rank Matrix