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

By Dan Li, Dacheng Chen, Lei Shi, Baihong Jin, Jonathan Goh, See-Kiong Ng. International Conference on Artificial Neural Networks, 2019

1,053 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/261e81cba749f70271fa4b7e230328fc1a4a6c96

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Signal Processing

Citations in the corpus

Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT (2021, methodology): “M is also reported as the number of features or variables in some literature [6], [13], [4].”
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series (2021, methodology): “2018a; Park, Hoshi, and Kemp 2018) and Generative Adversarial Networks (GAN) models (Zhou et al. 2019; Li et al. 2019), have found success in practical time series tasks.”
Progress in Outlier Detection Techniques: A Survey (2019, background): “Recently, more attention has been given to deep learning in many areas including several studies related to outlier detection problems [35], [36] [30], [207]–[209].”
Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines (2021, methodology): “GAN-based models explicitly generate samples that are as similar as possible to the input data with the generator, as in [53], [59], [74], [115].”
Deep Learning for Time Series Anomaly Detection: A Survey (2022, neutral): “In TS2Vec, positive pairs are representations at the same timestamp in two augmented contexts created by timestamp masking and random cropping, while negative samples are representations at different timestamps from the same series or from other series at the same timestamp within the batch.”
Multivariate Time-series Anomaly Detection via Graph Attention Network (2020, background): “GAN-Li [10], MAD-GAN [11] and LSTM-VAE [12].”
Machine Learning in IoT Security: Current Solutions and Future Challenges (2019, methodology): “For instance, GANs have been used for anomaly detection and intrusion detection in IoT networks [199]–[201], [213], [214]”
Anomaly Detection in Time Series: A Comprehensive Evaluation (2022, neutral): “NormalizingFlow [116] DeepAnT [94] STORN[123] CoalESN[99] DeepNAP [72] DeepLSTM[31] HybridKNN [124] EncDec-AD [88] LSTM-basedVAE-GAN[98] LAMP[166] DAE [117] MultiHTM[146] TCN-AE[135] AD-LTI [148] LSTM-AD [89] AE [117] VELC[158] Bagel [79] HealthESN [32] MTAD-GAT [161] MoteESN[30] RADM[40] MSCRED [15”
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy (2021, methodology): “For time series analysis, benefiting from the advantage of the self-attention mechanism, Transformers are used to discover the reliable long-range temporal dependencies (Kitaev et al., 2020; Li et al., 2019b; Zhou et al., 2021; Wu et al., 2021).”
Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network (2020, background): “Following [17, 28, 13, 31], we consider the unsupervised learning setting, and do not use any label information during training.”
Artificial intelligence based anomaly detection of energy consumption in buildings: A review, current trends and new perspectives (2021, background): “It can model complex and high-dimensional data of different types, including images [71], time-series [72, 73] and cyber security [74].”
TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data (2022, methodology): “We compare TranAD with state-of-the-art models for mutlivariate time-series anomaly detection, including MERLIN [37], LSTMNDT [20] (with autoencoder implementation from openGauss [30]), DAGMM [65], OmniAnomaly [45], MSCRED [60], MAD-GAN [29], USAD [4], MTAD-GAT [62], CAE-M [61] and GDN [14] (with gr”
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection (2023, background): “Recent works in time series anomaly detection also include generative adversarial networks (GANs) based methods [16, 16, 41, 91] and deep reinforcement learning (DRL) based methods [30, 84].”
Generative Adversarial Networks in Time Series: A Systematic Literature Review (2022, background): “Similar approaches have been applied to detect cardiovascular diseases [69], in cyber-physical systems to detect nefarious players [66], and even irregular behaviors such as stock manipulation on the stock markets [63].”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “Additionally, GANs have made achievements in sequential data tasks, such as those involving natural language, music, speech, voice [268], [269], and time series data [270], [271], [272], [273].”
An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series (2021, methodology): “In addition, we compare published results for OmniAnomaly, USAD [8] and MAD-GAN [3] with ours in section S5 in the SI.”