Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

Abstract

Anomaly detection has become an indispensable tool for modern society, applied in a wide range of applications, from detecting fraudulent transactions to malignant brain tumors. Over time, many anomaly detection techniques have been introduced. However, in general, they all suffer from the same problem: lack of data that represents anomalous behaviour. As anomalous behaviour is usually costly (or dangerous) for a system, it is difficult to gather enough data that represents such behaviour. This, in turn, makes it difficult to develop and evaluate anomaly detection techniques. Recently, generative adversarial networks (GANs) have attracted much attention in anomaly detection research, due to their unique ability to generate new data. In this paper, we present a systematic review of the literature in this area, covering 128 papers. The goal of this review paper is to analyze the relation between anomaly detection techniques and types of GANs, to identify the most common application domains for GAN-assisted and GAN-based anomaly detection, and to assemble information on datasets and performance metrics used to assess them. Our study helps researchers and practitioners to find the most suitable GAN-assisted anomaly detection technique for their application. In addition, we present a research roadmap for future studies in this area. In summary, GANs are used in anomaly detection to address the problem of insufficient amount of data for the anomalous behaviour, either through data augmentation or representation learning. The most commonly used GAN architectures are DCGANs, standard GANs, and cGANs. The primary application domains include medicine, surveillance and intrusion detection.

A Review of Machine Learning Approaches in Synchrophasor Technology

“…For such events, a whole data set training should be performed, followed by the use of realtime data events to validate and test the algorithm's efficacy. By shifting from an offline to an online environment, DL techniques such as autoencoder-based neural networks [186], generative adversarial networks (GAN) [187], and one-class support vector machines (OCSVMs) [188] can forecast the occurrence and type of fault. Moreover, a lot of the applications listed in [189] essentially evaluated the DL techniques used in electrical PS as a whole, but they may also be used successfully to investigate PS transmission as well as the side of distribution where PMUs and µPMUs are installed.…”

How much BiGAN and CycleGAN-learned hidden features are effective for COVID-19 detection from CT images? A comparative study

“…First, GANs can potentially help to generate hard-to-acquire anomalous data points. Second, they can be used to learn the distribution of data for normal operating conditions and, then, can be exploited as anomaly or outlier detectors [44]. A conditional GAN-based model, called CovidGAN, is proposed in [45], which generates synthetic chest X-ray images to augment the available training set.…”

Selective Microwave Zeroth-Order Resonator Sensor Aided by Machine Learning

“…At the same time, hand-crafted measurements are prone to error, especially for small concentrations of the desired MUT. To address the challenges associated with the use of CNN for material characterization, this paper introduces a technique to generate a large number of data points with high accuracy using a generative adversarial network (GAN) [ 27 , 28 ] called Style-GAN. It has been shown that GANs can be used for image generation [ 29 ], audio generation [ 30 ], and language processing [ 31 ].…”