A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security

Web applications are often exposed to attacks because of the critical information and valuable assets they host. In this study, Bi-LSTM based web application security models were developed in order to detect web attacks and classify them into binary or multiple classes using HTTP requests. A novel d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hacer Karacan, Mehmet Sevri
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Web security anomaly detection deep learning Bi-LSTM data augmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/eaf8645eb10b476b8d107ee7292c1a89
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:eaf8645eb10b476b8d107ee7292c1a89
record_format	dspace
spelling	oai:doaj.org-article:eaf8645eb10b476b8d107ee7292c1a892021-11-18T00:06:24ZA Novel Data Augmentation Technique and Deep Learning Model for Web Application Security2169-353610.1109/ACCESS.2021.3125785https://doaj.org/article/eaf8645eb10b476b8d107ee7292c1a892021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9605636/https://doaj.org/toc/2169-3536Web applications are often exposed to attacks because of the critical information and valuable assets they host. In this study, Bi-LSTM based web application security models were developed in order to detect web attacks and classify them into binary or multiple classes using HTTP requests. A novel data augmentation technique based on the self-adapting noise adding method (DA-SANA) was developed. The DA-SANA method solves the low sensitivity problem caused by imbalanced data and the complex structure of multi-class classification in web attack detection. Experimental evaluations are carried out in detail using two benchmark web security datasets and a newly created dataset within the scope of the study. The achieved worst case detection rates are 98.34% and 93.91% for binary-class and multi-class classifications, respectively. The proposed DA-SANA technique provides an average of 6.52% improvement in multi-class classification for two datasets. These results revealed that the best classification performance values were achieved when compared with previous studies.Hacer KaracanMehmet SevriIEEEarticleWeb securityanomaly detectiondeep learningBi-LSTMdata augmentationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 150781-150797 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Web security anomaly detection deep learning Bi-LSTM data augmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Web security anomaly detection deep learning Bi-LSTM data augmentation Electrical engineering. Electronics. Nuclear engineering TK1-9971 Hacer Karacan Mehmet Sevri A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security
description	Web applications are often exposed to attacks because of the critical information and valuable assets they host. In this study, Bi-LSTM based web application security models were developed in order to detect web attacks and classify them into binary or multiple classes using HTTP requests. A novel data augmentation technique based on the self-adapting noise adding method (DA-SANA) was developed. The DA-SANA method solves the low sensitivity problem caused by imbalanced data and the complex structure of multi-class classification in web attack detection. Experimental evaluations are carried out in detail using two benchmark web security datasets and a newly created dataset within the scope of the study. The achieved worst case detection rates are 98.34% and 93.91% for binary-class and multi-class classifications, respectively. The proposed DA-SANA technique provides an average of 6.52% improvement in multi-class classification for two datasets. These results revealed that the best classification performance values were achieved when compared with previous studies.
format	article
author	Hacer Karacan Mehmet Sevri
author_facet	Hacer Karacan Mehmet Sevri
author_sort	Hacer Karacan
title	A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security
title_short	A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security
title_full	A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security
title_fullStr	A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security
title_full_unstemmed	A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security
title_sort	novel data augmentation technique and deep learning model for web application security
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/eaf8645eb10b476b8d107ee7292c1a89
work_keys_str_mv	AT hacerkaracan anoveldataaugmentationtechniqueanddeeplearningmodelforwebapplicationsecurity AT mehmetsevri anoveldataaugmentationtechniqueanddeeplearningmodelforwebapplicationsecurity AT hacerkaracan noveldataaugmentationtechniqueanddeeplearningmodelforwebapplicationsecurity AT mehmetsevri noveldataaugmentationtechniqueanddeeplearningmodelforwebapplicationsecurity
_version_	1718425258430562304

A Novel Data Augmentation Technique and Deep Learning Model for Web Application Security

Ejemplares similares