A multimodal hybrid parallel network intrusion detection model

With the rapid growth of Internet data traffic, the means of malicious attack become more diversified. The single modal intrusion detection model cannot fully exploit the rich feature information in the massive network traffic data, resulting in unsatisfactory detection results. To address this issu...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuxin Shi, Dezhi Han, Mingming Cui
Format: Article
Language:English
Published: Taylor & Francis Group 2023-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2023.2227780
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850237033035857920
author Shuxin Shi
Dezhi Han
Mingming Cui
author_facet Shuxin Shi
Dezhi Han
Mingming Cui
author_sort Shuxin Shi
collection DOAJ
description With the rapid growth of Internet data traffic, the means of malicious attack become more diversified. The single modal intrusion detection model cannot fully exploit the rich feature information in the massive network traffic data, resulting in unsatisfactory detection results. To address this issue, this paper proposes a multimodal hybrid parallel network intrusion detection model (MHPN). The proposed model extracts network traffic features from two modalities: the statistical information of network traffic and the original load of traffic, and constructs appropriate neural network models for each modal information. Firstly, a two-branch convolutional neural network is combined with Long Short-Term Memory (LSTM) network to extract the spatio-temporal feature information of network traffic from the original load mode of traffic, and a convolutional neural network is used to extract the feature information of traffic statistics. Then, the feature information extracted from the two modalities is fused and fed to the CosMargin classifier for network traffic classification. The experimental results on the ISCX-IDS 2012 and CIC-IDS-2017 datasets show that the MHPN model outperforms the single-modal models and achieves an average accuracy of 99.98 $ \% $ . The model also demonstrates strong robustness and a positive sample recognition rate.
format Article
id doaj-art-3424074537d44aa38d54564aaba3d9b2
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2023-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-3424074537d44aa38d54564aaba3d9b22025-08-20T02:01:50ZengTaylor & Francis GroupConnection Science0954-00911360-04942023-12-0135110.1080/09540091.2023.22277802227780A multimodal hybrid parallel network intrusion detection modelShuxin Shi0Dezhi Han1Mingming Cui2Shanghai Maritime UniversityShanghai Maritime UniversityShanghai Maritime UniversityWith the rapid growth of Internet data traffic, the means of malicious attack become more diversified. The single modal intrusion detection model cannot fully exploit the rich feature information in the massive network traffic data, resulting in unsatisfactory detection results. To address this issue, this paper proposes a multimodal hybrid parallel network intrusion detection model (MHPN). The proposed model extracts network traffic features from two modalities: the statistical information of network traffic and the original load of traffic, and constructs appropriate neural network models for each modal information. Firstly, a two-branch convolutional neural network is combined with Long Short-Term Memory (LSTM) network to extract the spatio-temporal feature information of network traffic from the original load mode of traffic, and a convolutional neural network is used to extract the feature information of traffic statistics. Then, the feature information extracted from the two modalities is fused and fed to the CosMargin classifier for network traffic classification. The experimental results on the ISCX-IDS 2012 and CIC-IDS-2017 datasets show that the MHPN model outperforms the single-modal models and achieves an average accuracy of 99.98 $ \% $ . The model also demonstrates strong robustness and a positive sample recognition rate.http://dx.doi.org/10.1080/09540091.2023.2227780intrusion detectionnetwork trafficconvolutional neural networklong short-term memory (lstm)
spellingShingle Shuxin Shi
Dezhi Han
Mingming Cui
A multimodal hybrid parallel network intrusion detection model
Connection Science
intrusion detection
network traffic
convolutional neural network
long short-term memory (lstm)
title A multimodal hybrid parallel network intrusion detection model
title_full A multimodal hybrid parallel network intrusion detection model
title_fullStr A multimodal hybrid parallel network intrusion detection model
title_full_unstemmed A multimodal hybrid parallel network intrusion detection model
title_short A multimodal hybrid parallel network intrusion detection model
title_sort multimodal hybrid parallel network intrusion detection model
topic intrusion detection
network traffic
convolutional neural network
long short-term memory (lstm)
url http://dx.doi.org/10.1080/09540091.2023.2227780
work_keys_str_mv AT shuxinshi amultimodalhybridparallelnetworkintrusiondetectionmodel
AT dezhihan amultimodalhybridparallelnetworkintrusiondetectionmodel
AT mingmingcui amultimodalhybridparallelnetworkintrusiondetectionmodel
AT shuxinshi multimodalhybridparallelnetworkintrusiondetectionmodel
AT dezhihan multimodalhybridparallelnetworkintrusiondetectionmodel
AT mingmingcui multimodalhybridparallelnetworkintrusiondetectionmodel