Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection

Class imbalance is a common problem in network threat detection. Oversampling the minority class is regarded as a popular countermeasure by generating enough new minority samples. Generative adversarial network (GAN) is a typical generative model that can generate any number of artificial minority s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yanping Xu, Xiaoyu Zhang, Zhenliang Qiu, Xia Zhang, Jian Qiu, Hua Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi-Wiley 2021
Materias:	Technology (General) T1-995 Science (General) Q1-390
Acceso en línea:	https://doaj.org/article/7a3475a20f2243a9be0d3e6b5809238a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7a3475a20f2243a9be0d3e6b5809238a
record_format	dspace
spelling	oai:doaj.org-article:7a3475a20f2243a9be0d3e6b5809238a2021-11-15T01:19:53ZOversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection1939-012210.1155/2021/9206440https://doaj.org/article/7a3475a20f2243a9be0d3e6b5809238a2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/9206440https://doaj.org/toc/1939-0122Class imbalance is a common problem in network threat detection. Oversampling the minority class is regarded as a popular countermeasure by generating enough new minority samples. Generative adversarial network (GAN) is a typical generative model that can generate any number of artificial minority samples, which are close to the real data. However, it is difficult to train GAN, and the Nash equilibrium is almost impossible to achieve. Therefore, in order to improve the training stability of GAN for oversampling to detect the network threat, a convergent WGAN-based oversampling model called convergent WGAN (CWGAN) is proposed in this paper. The training process of CWGAN contains multiple iterations. In each iteration, the training epochs of the discriminator are dynamic, which is determined by the convergence of discriminator loss function in the last two iterations. When the discriminator is trained to convergence, the generator will then be trained to generate new minority samples. The experiment results show that CWGAN not only improve the training stability of WGAN on the loss smoother and closer to 0 but also improve the performance of the minority class through oversampling, which means that CWGAN can improve the performance of network threat detection.Yanping XuXiaoyu ZhangZhenliang QiuXia ZhangJian QiuHua ZhangHindawi-WileyarticleTechnology (General)T1-995Science (General)Q1-390ENSecurity and Communication Networks, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology (General) T1-995 Science (General) Q1-390
spellingShingle	Technology (General) T1-995 Science (General) Q1-390 Yanping Xu Xiaoyu Zhang Zhenliang Qiu Xia Zhang Jian Qiu Hua Zhang Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection
description	Class imbalance is a common problem in network threat detection. Oversampling the minority class is regarded as a popular countermeasure by generating enough new minority samples. Generative adversarial network (GAN) is a typical generative model that can generate any number of artificial minority samples, which are close to the real data. However, it is difficult to train GAN, and the Nash equilibrium is almost impossible to achieve. Therefore, in order to improve the training stability of GAN for oversampling to detect the network threat, a convergent WGAN-based oversampling model called convergent WGAN (CWGAN) is proposed in this paper. The training process of CWGAN contains multiple iterations. In each iteration, the training epochs of the discriminator are dynamic, which is determined by the convergence of discriminator loss function in the last two iterations. When the discriminator is trained to convergence, the generator will then be trained to generate new minority samples. The experiment results show that CWGAN not only improve the training stability of WGAN on the loss smoother and closer to 0 but also improve the performance of the minority class through oversampling, which means that CWGAN can improve the performance of network threat detection.
format	article
author	Yanping Xu Xiaoyu Zhang Zhenliang Qiu Xia Zhang Jian Qiu Hua Zhang
author_facet	Yanping Xu Xiaoyu Zhang Zhenliang Qiu Xia Zhang Jian Qiu Hua Zhang
author_sort	Yanping Xu
title	Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection
title_short	Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection
title_full	Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection
title_fullStr	Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection
title_full_unstemmed	Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection
title_sort	oversampling imbalanced data based on convergent wgan for network threat detection
publisher	Hindawi-Wiley
publishDate	2021
url	https://doaj.org/article/7a3475a20f2243a9be0d3e6b5809238a
work_keys_str_mv	AT yanpingxu oversamplingimbalanceddatabasedonconvergentwganfornetworkthreatdetection AT xiaoyuzhang oversamplingimbalanceddatabasedonconvergentwganfornetworkthreatdetection AT zhenliangqiu oversamplingimbalanceddatabasedonconvergentwganfornetworkthreatdetection AT xiazhang oversamplingimbalanceddatabasedonconvergentwganfornetworkthreatdetection AT jianqiu oversamplingimbalanceddatabasedonconvergentwganfornetworkthreatdetection AT huazhang oversamplingimbalanceddatabasedonconvergentwganfornetworkthreatdetection
_version_	1718428930203975680

Oversampling Imbalanced Data Based on Convergent WGAN for Network Threat Detection

Ejemplares similares