Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning

Network intrusion detection focuses on classifying network traffic as either normal or attack carrier. The classification is based on information extracted from the network flow packets. This is a complex classification problem with unbalanced datasets and noisy data. This work extends the classic r...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Manuel Lopez-Martin, Antonio Sanchez-Esguevillas, Juan Ignacio Arribas, Belen Carro
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Communication system security intrusion detection neural networks radial basis function networks Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/4c5892a1fbab46b99d8583544066a80e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4c5892a1fbab46b99d8583544066a80e
record_format	dspace
spelling	oai:doaj.org-article:4c5892a1fbab46b99d8583544066a80e2021-11-20T00:02:05ZNetwork Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning2169-353610.1109/ACCESS.2021.3127689https://doaj.org/article/4c5892a1fbab46b99d8583544066a80e2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9612220/https://doaj.org/toc/2169-3536Network intrusion detection focuses on classifying network traffic as either normal or attack carrier. The classification is based on information extracted from the network flow packets. This is a complex classification problem with unbalanced datasets and noisy data. This work extends the classic radial basis function (RBF) neural network by including it as a policy network in an offline reinforcement learning algorithm. With this approach, all parameters of the radial basis functions (along with the network weights) are learned end-to-end by gradient descent without external optimization. We further explore how additional dense hidden-layers, and the number of radial basis kernels influence the results. This novel approach is applied to five prominent intrusion detection datasets (NSL-KDD, UNSW-NB15, AWID, CICIDS2017 and CICDDOS2019) achieving better performance metrics than alternative state-of-the-art models. Each dataset provides different restrictions and challenges allowing a better validation of results. Analysis of the results shows that the proposed architectures are excellent candidates for designing classifiers with the constraints imposed by network intrusion detection. We discuss the importance of dataset imbalance and how the proposed methods may be critically important for unbalanced datasets.Manuel Lopez-MartinAntonio Sanchez-EsguevillasJuan Ignacio ArribasBelen CarroIEEEarticleCommunication system securityintrusion detectionneural networksradial basis function networksElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 153153-153170 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Communication system security intrusion detection neural networks radial basis function networks Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Communication system security intrusion detection neural networks radial basis function networks Electrical engineering. Electronics. Nuclear engineering TK1-9971 Manuel Lopez-Martin Antonio Sanchez-Esguevillas Juan Ignacio Arribas Belen Carro Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning
description	Network intrusion detection focuses on classifying network traffic as either normal or attack carrier. The classification is based on information extracted from the network flow packets. This is a complex classification problem with unbalanced datasets and noisy data. This work extends the classic radial basis function (RBF) neural network by including it as a policy network in an offline reinforcement learning algorithm. With this approach, all parameters of the radial basis functions (along with the network weights) are learned end-to-end by gradient descent without external optimization. We further explore how additional dense hidden-layers, and the number of radial basis kernels influence the results. This novel approach is applied to five prominent intrusion detection datasets (NSL-KDD, UNSW-NB15, AWID, CICIDS2017 and CICDDOS2019) achieving better performance metrics than alternative state-of-the-art models. Each dataset provides different restrictions and challenges allowing a better validation of results. Analysis of the results shows that the proposed architectures are excellent candidates for designing classifiers with the constraints imposed by network intrusion detection. We discuss the importance of dataset imbalance and how the proposed methods may be critically important for unbalanced datasets.
format	article
author	Manuel Lopez-Martin Antonio Sanchez-Esguevillas Juan Ignacio Arribas Belen Carro
author_facet	Manuel Lopez-Martin Antonio Sanchez-Esguevillas Juan Ignacio Arribas Belen Carro
author_sort	Manuel Lopez-Martin
title	Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning
title_short	Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning
title_full	Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning
title_fullStr	Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning
title_full_unstemmed	Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning
title_sort	network intrusion detection based on extended rbf neural network with offline reinforcement learning
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/4c5892a1fbab46b99d8583544066a80e
work_keys_str_mv	AT manuellopezmartin networkintrusiondetectionbasedonextendedrbfneuralnetworkwithofflinereinforcementlearning AT antoniosanchezesguevillas networkintrusiondetectionbasedonextendedrbfneuralnetworkwithofflinereinforcementlearning AT juanignacioarribas networkintrusiondetectionbasedonextendedrbfneuralnetworkwithofflinereinforcementlearning AT belencarro networkintrusiondetectionbasedonextendedrbfneuralnetworkwithofflinereinforcementlearning
_version_	1718419829958901760

Network Intrusion Detection Based on Extended RBF Neural Network With Offline Reinforcement Learning

Ejemplares similares