A neural convolutional network intrusion detection model based on autoencoder dimension reduction

In order to improve the accuracy of intrusion detection,considering the advantages of autoencoders in learning features and the mature application of residual networks in constructing deep models,an improved residual network intrusion detection model based on feature dimensionality reduction(IRFD)wa...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Dianxin Kexue Ročník 41; číslo 2; s. 129 - 138
Hlavní autoři: Sun, Jing, Ding, Jiawei, Feng, Guanghui
Médium: Journal Article
Jazyk:čínština
angličtina
Vydáno: Bejing China International Book Trading 01.02.2025
Beijing Xintong Media Co., Ltd
Témata:
Accuracy
convolutional attention mechanism
Datasets
intrusion detection model
Machine learning
network attack
residual network
stacking denoising sparse autoencoder
ISSN:1000-0801
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In order to improve the accuracy of intrusion detection,considering the advantages of autoencoders in learning features and the mature application of residual networks in constructing deep models,an improved residual network intrusion detection model based on feature dimensionality reduction(IRFD)was proposed.The goal of the proposed IRFD was to solve the issue of low detection accuracy of traditional machine learning based intrusion detec-tion models.In IRFD,the stacking denoising sparse autoencoder was employed to reduce the dimensionality of fea-tures and extract effective features.The convolutional attention mechanism was used to improve the residual network and form a classification network that could extract key features.Two typical intrusion detection datasets were em-ployed to verify the detection performance of the IRFD.Experimental results demonstrate that the detection accuracy of the proposed IRFD on the both UNSW-NB15 and CICIDS 2017 datasets are over 99%,with F1-score of 99.5%and 99.7%,respectively.Compared with the state-of-the-art models for the intrusion detection,the accuracy,preci-sion,and F1-score performance of the IRFD were significantly improved.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1000-0801
DOI:10.11959/j.issn.1000-0801.2025002