An intrusion detection method based on depthwise separable convolution and attention mechanism

In order to improve the accuracy of multi-classification in network intrusion detection, an intrusion detection method was proposed based on depthwise separable convolution and attention mechanism.By constructing a cascade structure combining depthwise separable convolution and long-term and short-t...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhifei ZHANG, Feng LIU, Yiyang GE, Shuo LI, Yu ZHANG, Ke XIONG
Format: Article
Language:zho
Published: China InfoCom Media Group 2023-03-01
Series:物联网学报
Subjects:
Online Access:http://www.wlwxb.com.cn/thesisDetails#10.11959/j.issn.2096-3750.2023.00307
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212419088941056
author Zhifei ZHANG
Feng LIU
Yiyang GE
Shuo LI
Yu ZHANG
Ke XIONG
author_facet Zhifei ZHANG
Feng LIU
Yiyang GE
Shuo LI
Yu ZHANG
Ke XIONG
author_sort Zhifei ZHANG
collection DOAJ
description In order to improve the accuracy of multi-classification in network intrusion detection, an intrusion detection method was proposed based on depthwise separable convolution and attention mechanism.By constructing a cascade structure combining depthwise separable convolution and long-term and short-term memory networks, the spatial and temporal features of network traffic data can be better extracted.A mixed-domain attention mechanism was introduced to enhance the detection performance.To solve the problem of low detection rate in some samples, a data balance strategy based on the combination of the variational auto-encoder (VAE) the generative adversarial network (GAN) and was designed, which can effectively cope with imbalanced datasets and improve the adaptability of the proposed detection method.The experimental results show that the proposed method is able to achieve 99.80%, 99.32%, and 83.87% accuracy on the CICIDS-2017, NSL-KDD and UNSW-NB15 datasets, which is improved by 0.6%, 0.5%, and 2.3%, respectively.
format Article
id doaj-art-c62c80ccc7134d7b974e29e92bc0cebe
institution OA Journals
issn 2096-3750
language zho
publishDate 2023-03-01
publisher China InfoCom Media Group
record_format Article
series 物联网学报
spelling doaj-art-c62c80ccc7134d7b974e29e92bc0cebe2025-08-20T02:09:21ZzhoChina InfoCom Media Group物联网学报2096-37502023-03-017495959579206An intrusion detection method based on depthwise separable convolution and attention mechanismZhifei ZHANGFeng LIUYiyang GEShuo LIYu ZHANGKe XIONGIn order to improve the accuracy of multi-classification in network intrusion detection, an intrusion detection method was proposed based on depthwise separable convolution and attention mechanism.By constructing a cascade structure combining depthwise separable convolution and long-term and short-term memory networks, the spatial and temporal features of network traffic data can be better extracted.A mixed-domain attention mechanism was introduced to enhance the detection performance.To solve the problem of low detection rate in some samples, a data balance strategy based on the combination of the variational auto-encoder (VAE) the generative adversarial network (GAN) and was designed, which can effectively cope with imbalanced datasets and improve the adaptability of the proposed detection method.The experimental results show that the proposed method is able to achieve 99.80%, 99.32%, and 83.87% accuracy on the CICIDS-2017, NSL-KDD and UNSW-NB15 datasets, which is improved by 0.6%, 0.5%, and 2.3%, respectively.http://www.wlwxb.com.cn/thesisDetails#10.11959/j.issn.2096-3750.2023.00307deep learning;intrusion detection;attention mechanism;generative adversarial network
spellingShingle Zhifei ZHANG
Feng LIU
Yiyang GE
Shuo LI
Yu ZHANG
Ke XIONG
An intrusion detection method based on depthwise separable convolution and attention mechanism
物联网学报
deep learning;intrusion detection;attention mechanism;generative adversarial network
title An intrusion detection method based on depthwise separable convolution and attention mechanism
title_full An intrusion detection method based on depthwise separable convolution and attention mechanism
title_fullStr An intrusion detection method based on depthwise separable convolution and attention mechanism
title_full_unstemmed An intrusion detection method based on depthwise separable convolution and attention mechanism
title_short An intrusion detection method based on depthwise separable convolution and attention mechanism
title_sort intrusion detection method based on depthwise separable convolution and attention mechanism
topic deep learning;intrusion detection;attention mechanism;generative adversarial network
url http://www.wlwxb.com.cn/thesisDetails#10.11959/j.issn.2096-3750.2023.00307
work_keys_str_mv AT zhifeizhang anintrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT fengliu anintrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT yiyangge anintrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT shuoli anintrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT yuzhang anintrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT kexiong anintrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT zhifeizhang intrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT fengliu intrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT yiyangge intrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT shuoli intrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT yuzhang intrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism
AT kexiong intrusiondetectionmethodbasedondepthwiseseparableconvolutionandattentionmechanism