IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism

Abstract Network attacks are illegal activities on digital resources within an organizational network with the express intention of compromising systems. A cyber attack can be directed by individuals, communities, states or even from an anonymous source. Hackers commonly conduct network attacks to a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	FatimaEzzahra Laghrissi, Samira Douzi, Khadija Douzi, Badr Hssina
Formato:	article
Lenguaje:	EN
Publicado:	SpringerOpen 2021
Materias:	Intrusion detection systems Deep learning Attention mechanism LSTM UMAP Chi-Square Computer engineering. Computer hardware TK7885-7895 Information technology T58.5-58.64 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/43294da0d6c24bb7957af3fd39148911
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:43294da0d6c24bb7957af3fd39148911
record_format	dspace
spelling	oai:doaj.org-article:43294da0d6c24bb7957af3fd391489112021-12-05T12:03:22ZIDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism10.1186/s40537-021-00544-52196-1115https://doaj.org/article/43294da0d6c24bb7957af3fd391489112021-11-01T00:00:00Zhttps://doi.org/10.1186/s40537-021-00544-5https://doaj.org/toc/2196-1115Abstract Network attacks are illegal activities on digital resources within an organizational network with the express intention of compromising systems. A cyber attack can be directed by individuals, communities, states or even from an anonymous source. Hackers commonly conduct network attacks to alter, damage, or steal private data. Intrusion detection systems (IDS) are the best and most effective techniques when it comes to tackle these threats. An IDS is a software application or hardware device that monitors traffic to search for malevolent activity or policy breaches. Moreover, IDSs are designed to be deployed in different environments, and they can either be host-based or network-based. A host-based intrusion detection system is installed on the client computer, while a network-based intrusion detection system is located on the network. IDSs based on deep learning have been used in the past few years and proved their effectiveness. However, these approaches produce a big false negative rate, which impacts the performance and potency of network security. In this paper, a detection model based on long short-term memory (LSTM) and Attention mechanism is proposed. Furthermore, we used four reduction algorithms, namely: Chi-Square, UMAP, Principal Components Analysis (PCA), and Mutual information. In addition, we evaluated the proposed approaches on the NSL-KDD dataset. The experimental results demonstrate that using Attention with all features and using PCA with 03 components had the best performance, reaching an accuracy of 99.09% and 98.49% for binary and multiclass classification, respectively.FatimaEzzahra LaghrissiSamira DouziKhadija DouziBadr HssinaSpringerOpenarticleIntrusion detection systemsDeep learningAttention mechanismLSTMUMAPChi-SquareComputer engineering. Computer hardwareTK7885-7895Information technologyT58.5-58.64Electronic computers. Computer scienceQA75.5-76.95ENJournal of Big Data, Vol 8, Iss 1, Pp 1-21 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Intrusion detection systems Deep learning Attention mechanism LSTM UMAP Chi-Square Computer engineering. Computer hardware TK7885-7895 Information technology T58.5-58.64 Electronic computers. Computer science QA75.5-76.95
spellingShingle	Intrusion detection systems Deep learning Attention mechanism LSTM UMAP Chi-Square Computer engineering. Computer hardware TK7885-7895 Information technology T58.5-58.64 Electronic computers. Computer science QA75.5-76.95 FatimaEzzahra Laghrissi Samira Douzi Khadija Douzi Badr Hssina IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism
description	Abstract Network attacks are illegal activities on digital resources within an organizational network with the express intention of compromising systems. A cyber attack can be directed by individuals, communities, states or even from an anonymous source. Hackers commonly conduct network attacks to alter, damage, or steal private data. Intrusion detection systems (IDS) are the best and most effective techniques when it comes to tackle these threats. An IDS is a software application or hardware device that monitors traffic to search for malevolent activity or policy breaches. Moreover, IDSs are designed to be deployed in different environments, and they can either be host-based or network-based. A host-based intrusion detection system is installed on the client computer, while a network-based intrusion detection system is located on the network. IDSs based on deep learning have been used in the past few years and proved their effectiveness. However, these approaches produce a big false negative rate, which impacts the performance and potency of network security. In this paper, a detection model based on long short-term memory (LSTM) and Attention mechanism is proposed. Furthermore, we used four reduction algorithms, namely: Chi-Square, UMAP, Principal Components Analysis (PCA), and Mutual information. In addition, we evaluated the proposed approaches on the NSL-KDD dataset. The experimental results demonstrate that using Attention with all features and using PCA with 03 components had the best performance, reaching an accuracy of 99.09% and 98.49% for binary and multiclass classification, respectively.
format	article
author	FatimaEzzahra Laghrissi Samira Douzi Khadija Douzi Badr Hssina
author_facet	FatimaEzzahra Laghrissi Samira Douzi Khadija Douzi Badr Hssina
author_sort	FatimaEzzahra Laghrissi
title	IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism
title_short	IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism
title_full	IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism
title_fullStr	IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism
title_full_unstemmed	IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism
title_sort	ids-attention: an efficient algorithm for intrusion detection systems using attention mechanism
publisher	SpringerOpen
publishDate	2021
url	https://doaj.org/article/43294da0d6c24bb7957af3fd39148911
work_keys_str_mv	AT fatimaezzahralaghrissi idsattentionanefficientalgorithmforintrusiondetectionsystemsusingattentionmechanism AT samiradouzi idsattentionanefficientalgorithmforintrusiondetectionsystemsusingattentionmechanism AT khadijadouzi idsattentionanefficientalgorithmforintrusiondetectionsystemsusingattentionmechanism AT badrhssina idsattentionanefficientalgorithmforintrusiondetectionsystemsusingattentionmechanism
_version_	1718372309823127552

IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism

Ejemplares similares