Full Text:   <1132>

CLC number: 

On-line Access: 2025-07-28

Received: 2024-05-30

Revision Accepted: 2024-09-18

Crosschecked: 2025-07-30

Cited: 0

Clicked: 944

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Jue CHEN

https://orcid.org/0000-0001-7508-2635

Xihe QIU

https://orcid.org/0000-0003-4024-925X

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2025 Vol.26 No.7 P.1115-1130

http://doi.org/10.1631/FITEE.2400459


CRGT-SA: an interlaced and spatiotemporal deep learning model for network intrusion detection


Author(s):  Jue CHEN, Wanxiao LIU, Xihe QIU, Wenjing LV, Yujie XIONG

Affiliation(s):  School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 310027, China

Corresponding email(s):   qiuxihe@sues.edu.cn

Key Words:  Intrusion detection, Deep learning, Convolutional neural network, Long short-term memory, Temporal convolutional network


Jue CHEN, Wanxiao LIU, Xihe QIU, Wenjing LV, Yujie XIONG. CRGT-SA: an interlaced and spatiotemporal deep learning model for network intrusion detection[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(7): 1115-1130.

@article{title="CRGT-SA: an interlaced and spatiotemporal deep learning model for network intrusion detection",
author="Jue CHEN, Wanxiao LIU, Xihe QIU, Wenjing LV, Yujie XIONG",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="26",
number="7",
pages="1115-1130",
year="2025",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2400459"
}

%0 Journal Article
%T CRGT-SA: an interlaced and spatiotemporal deep learning model for network intrusion detection
%A Jue CHEN
%A Wanxiao LIU
%A Xihe QIU
%A Wenjing LV
%A Yujie XIONG
%J Frontiers of Information Technology & Electronic Engineering
%V 26
%N 7
%P 1115-1130
%@ 2095-9184
%D 2025
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2400459

TY - JOUR
T1 - CRGT-SA: an interlaced and spatiotemporal deep learning model for network intrusion detection
A1 - Jue CHEN
A1 - Wanxiao LIU
A1 - Xihe QIU
A1 - Wenjing LV
A1 - Yujie XIONG
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 26
IS - 7
SP - 1115
EP - 1130
%@ 2095-9184
Y1 - 2025
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2400459


Abstract: 
To address the challenge of cyberattacks, intrusion detection systems (IDSs) are introduced to recognize intrusions and protect computer networks. Among all these IDSs, conventional machine learning methods rely on shallow learning and have unsatisfactory performance. Unlike machine learning methods, deep learning methods are the mainstream methods because of their capability to handle mass data without prior knowledge of specific domain expertise. Concerning deep learning, long short-term memory (LSTM) and temporal convolutional networks (TCNs) can be used to extract temporal features from different angles, while convolutional neural networks (CNNs) are valuable for learning spatial properties. Based on the above, this paper proposes a novel interlaced and spatiotemporal deep learning model called CRGT-SA, which combines CNN with gated TCN and recurrent neural network (RNN) modules to learn spatiotemporal properties, and imports the self-attention mechanism to select significant features. More specifically, our proposed model splits the feature extraction into multiple steps with a gradually increasing granularity, and executes each step with a combined CNN, LSTM, and gated TCN module. Our proposed CRGT-SA model is validated using the UNSW-NB15 dataset and is compared with other compelling techniques, including traditional machine learning and deep learning models as well as state-of-the-art deep learning models. According to the simulation results, our proposed model exhibits the highest accuracy and F1-score among all the compared methods. More specifically, our proposed model achieves 91.5% and 90.5% accuracy for binary and multi-class classifications respectively, and demonstrates its ability to protect the Internet from complicated cyberattacks. Moreover, we conduct another series of simulations on the NSL-KDD dataset; the simulation results of comparison with other models further prove the generalization ability of our proposed model.

CRGT-SA:基于交错式时空深度学习的网络入侵检测模型

陈珏,刘皖肖,邱禧荷,吕文静,熊玉洁
上海工程技术大学电子电气工程学院,中国上海市,310027
摘要:为应对网络攻击的挑战,人们引入入侵检测系统以识别入侵行为并保护计算机网络。在所有这些入侵检测系统中,传统机器学习方法依赖于浅学习,其性能不理想。与机器学习方法不同,深度学习方法是目前主流方法,因其能处理大量数据,而无需事先了解特定领域的专业知识。在深度学习中,长短期记忆(LSTM)和时间卷积网络(TCN)可以从不同角度提取时间特征,而卷积神经网络(CNN)则可以学习空间特征。基于此背景,本文提出一种新的交错式时空深度学习模型(CRGT-SA),该模型将CNN与门控TCN和LSTM模块结合以学习时空特性,并引入自注意力机制选择显著特征。具体而言,所提模型将特征提取分解为粒度逐渐增加的多个步骤,并结合CNN、LSTM和门控TCN模块执行每个步骤。基于UNSW-NB15数据集对所提CRGT-SA模型进行验证,并与其他方法比较,包括传统机器学习、深度学习模型以及最先进的深度学习模型。仿真结果表明,所提模型具有最高准确率和F1值。所提模型在二分类和多分类上的准确率分别为91.5%和90.5%,证明其保护互联网免受复杂网络攻击的能力。此外,在NSL-KDD数据集上进行了一系列模拟,并与其他模型比较;仿真结果进一步证明该模型的泛化能力。

关键词:入侵检测;深度学习;卷积神经网络;长短期记忆网络;时间卷积网络

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Abdel-Basset M, Hawash H, Chakrabortty RK, et al., 2021. Semi-supervised spatiotemporal deep learning for intrusions detection in IoT networks. IEEE Int Things J, 8(15):12251-12265.

[2]Abdelmoumin G, Rawat DB, Rahman A, 2022. On the performance of machine learning models for anomaly-based intelligent intrusion detection systems for the Internet of Things. IEEE Int Things J, 9(6):4280-4290.

[3]Abeshu A, Chilamkurti N, 2018. Deep learning: the frontier for distributed attack detection in fog-to-things computing. IEEE Commun Mag, 56(2):169-175.

[4]Aldweesh A, Derhab A, Emam AZ, 2020. Deep learning approaches for anomaly-based intrusion detection systems: a survey, taxonomy, and open issues. Knowl Based Syst, 189: 105124.

[5]Al-Garadi MA, Mohamed A, Al-Ali AK, et al., 2020. A survey of machine and deep learning methods for Internet of Things (IoT) security. IEEE Commun Surv Tutor, 22(3):1646-1685.

[6]Cao B, Li CH, Song YF, et al., 2022. Network intrusion detection model based on CNN and GRU. Appl Sci, 12(9):4184.

[7]Chen J, Xiong YJ, Qiu XH, et al., 2022. A cross entropy based approach to minimum propagation latency for controller placement in software defined network. Comput Commun, 191:133-144.

[8]Cook AA, Misirli G, Fan Z, 2020. Anomaly detection for IoT time-series data: a survey. IEEE Int Things J, 7(7):6481-6494.

[9]Fang LM, Li Y, Liu Z, et al., 2021. A practical model based on anomaly detection for protecting medical IoT control services against external attacks. IEEE Trans Ind Inform, 17(6):4260-4269.

[10]Fenghour S, Chen DQ, Guo K, et al., 2021. Deep learning-based automated lip-reading: a survey. IEEE Access, 9:121184-121205.

[11]Gan BQ, Chen YQ, Dong QP, et al., 2022. A convolutional neural network intrusion detection method based on data imbalance. J Supercomput, 78(18):19401-19434.

[12]Hassan MM, Gumaei A, Alsanad A, et al., 2020. A hybrid deep learning model for efficient intrusion detection in big data environment. Inform Sci, 513:386-396.

[13]Jian SL, Pang GS, Cao LB, et al., 2019. CURE: flexible categorical data representation by hierarchical coupling learning. IEEE Trans Knowl Data Eng, 31(5):853-866.

[14]Kasongo SM, 2023. A deep learning technique for intrusion detection system using a recurrent neural networks based framework. Comput Commun, 199:113-125.

[15]Khan MA, 2021. HCRNNIDS: hybrid convolutional recurrent neural network-based network intrusion detection system. Processes, 9(5):834.

[16]Khan MA, Iqbal N, Imran N, et al., 2023. An optimized ensemble prediction model using AutoML based on soft voting classifier for network intrusion detection. J Netw Comput Appl, 212: 103560.

[17]Kumar R, Kumar P, Tripathi R, et al., 2022. P2SF-IoV: a privacy-preservation-based secured framework for Internet of Vehicles. IEEE Trans Intell Transp Syst, 23(11):22571-22582.

[18]Laghrissi F, Douzi S, Douzi K, et al., 2021. Intrusion detection systems using long short-term memory (LSTM). J Big Data, 8(1):65.

[19]Lv ZH, Qiao L, Li JH, et al., 2021. Deep-learning-enabled security issues in the Internet of Things. IEEE Int Things J, 8(12):9531-9538.

[20]Marteau PF, 2021. Random partitioning forest for point-wise and collective anomaly detection—application to network intrusion detection. IEEE Trans Inform Forens Secur, 16:2157-2172.

[21]Moustafa N, Slay J, 2016. The evaluation of network anomaly detection systems: statistical analysis of the UNSW-NB15 dataset and the comparison with the KDD99 dataset. Inform Secur J Glob Perspect, 25(1-3):18-31.

[22]Nie LS, Wu YX, Wang XJ, et al., 2022. Intrusion detection for secure social Internet of Things based on collaborative edge computing: a generative adversarial network-based approach. IEEE Trans Comput Soc Syst, 9(1):134-145.

[23]Oseni A, Moustafa N, Creech G, et al., 2023. An explainable deep learning framework for resilient intrusion detection in IoT-enabled transportation networks. IEEE Trans Intell Transp Syst, 24(1):1000-1014.

[24]Qi LY, Yang YH, Zhou XK, et al., 2022. Fast anomaly identification based on multiaspect data streams for intelligent intrusion detection toward secure Industry 4.0. IEEE Trans Ind Inform, 18(9):6503-6511.

[25]Vasilomanolakis E, Karuppayah S, Mühlhäuser M, et al., 2015. Taxonomy and survey of collaborative intrusion detection. ACM Comput Surv, 47(4):55.

[26]Vinayakumar R, Alazab M, Soman KP, et al., 2019. Deep learning approach for intelligent intrusion detection system. IEEE Access, 7:41525-41550.

[27]Wahab OA, 2022. Intrusion detection in the IoT under data and concept drifts: online deep learning approach. IEEE Int Things J, 9(20):19706-19716.

[28]Wang K, Zhang AH, Sun HR, et al., 2023. Analysis of recent deep-learning-based intrusion detection methods for in-vehicle network. IEEE Trans Intell Transp Syst, 24(2):1843-1854.

[29]Wang W, Sheng YQ, Wang JL, et al., 2018. HAST-IDS: learning hierarchical spatial-temporal features using deep neural networks to improve intrusion detection. IEEE Access, 6:1792-1806.

[30]Wang XF, Han YW, Leung VCM, et al., 2020. Convergence of edge computing and deep learning: a comprehensive survey. IEEE Commun Surv Tutor, 22(2):869-904.

[31]Wu PL, Guo H, 2019. LuNet: a deep neural network for network intrusion detection. IEEE Symp Series on Computational Intelligence, p.617-624.

[32]Zhang JW, Ling Y, Fu XB, et al., 2020. Model of the intrusion detection system based on the integration of spatial-temporal features. Comput Secur, 89: 101681.

[33]Zhuo XY, Zhang JL, Son SW, 2017. Network intrusion detection using word embeddings. IEEE Int Conf on Big Data, p.4686-4695.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2025 Journal of Zhejiang University-SCIENCE