基于深度学习和SVM-RFE的网络入侵检测模型

叶青; 张延年; 吴昊

doi:10.11959/j.issn.1000-0801.2025100

您当前的位置：

首页 >

文章列表页 >

基于深度学习和SVM-RFE的网络入侵检测模型

研究与开发 | 更新时间：2025-08-07

- 基于深度学习和SVM-RFE的网络入侵检测模型
- Deep learning and support vector machine-recursive feature elimination-based network intrusion detection model
- 电信科学 2025年41卷第7期页码：108-119
- 作者机构：
  
  1.江苏省高港中等专业学校，江苏泰州 225324
  2.南京交通职业技术学院电子信息工程学院，江苏南京 211188
- 作者简介：
  
  [ "叶青（1973- ），男，江苏省高港中等专业学校讲师，主要研究方向为人工智能、物联网应用。" ]
  [ "张延年（1977- ），男，南京交通职业技术学院电子信息工程学院副教授，主要研究方向为大数据、人工智能。" ]
  [ "吴昊（1973- ），男，南京交通职业技术学院电子信息工程学院教授，主要研究方向为智能交通、计算机网络。" ]
- 基金信息：
  
  南京交通职业技术学院重大课题项目(JZ2304);南京交通职业技术学院重点课题项目(JZ2306)
- DOI：10.11959/j.issn.1000-0801.2025100
  中图分类号： TP393
- 收稿：2024-10-11，
  
  修回：2024-12-18，
  
  纸质出版：2025-07-20
- 稿件说明：
移动端阅览
叶青,张延年,吴昊.基于深度学习和SVM-RFE的网络入侵检测模型[J].电信科学,2025,41(07):108-119.

YE Qing,ZHANG Yannian,WU Hao.Deep learning and support vector machine-recursive feature elimination-based network intrusion detection model[J].Telecommunications Science,2025,41(07):108-119.
叶青,张延年,吴昊.基于深度学习和SVM-RFE的网络入侵检测模型[J].电信科学,2025,41(07):108-119. DOI： 10.11959/j.issn.1000-0801.2025100.

YE Qing,ZHANG Yannian,WU Hao.Deep learning and support vector machine-recursive feature elimination-based network intrusion detection model[J].Telecommunications Science,2025,41(07):108-119. DOI： 10.11959/j.issn.1000-0801.2025100.

摘要

网络入侵检测系统是对抗各种网络威胁的有效手段。然而，网络入侵数据中存在大量冗余信息和分布不平衡问题，为此，提出基于深度学习和支持向量机的递归特征消除算法的网络入侵检测（DLRF）模型。DLRF模型利用基于支持向量机的递归特征消除算法进行特征权重排序，选择重要特征。同时，结合过采样和欠采样技术解决数据样本分布不平衡的问题。利用3个深度学习算法构建集成框架的基学习器，并利用深度神经网络构建元学习器，进而提升DLRF模型检测网络攻击的性能。通过两个典型的网络入侵数据集UNSW-NB15和数据集CICIDS 2017验证DLRF模型的性能。性能分析表明，DLRF模型在这两个数据集上的准确率分别为0.906 8、0.996 8，F1值（F1-score）分别为0.906 8、0.996 0。

Abstract

Network intrusion detection system has gained attention as an effective means of combating various cyber threats. However

there are a lot of redundant information and unbalanced distribution problems in network intrusion data

therefore

deep learning and support vector machine-recursive feature elimination-based network intrusion detection model (DLRF) was proposed. The features were sorted by the support vector machine-recursive feature elimination algorithm and the important features were selected. Moreover

both oversampling and under-sampling techniques were utilized to tackle the unbalance problem of data sample distribution. Three deep learning algorithms were used to build the base learner of the ensemble framework

and deep neural network was used to build the meta-learner

so as to improve the performance of DLRF model to detect network attacks. The proposed framework was experimented with two publicly available and popular network traffic datasets

namely UNSW-NB15 and CICIDS-2017. The accuracy rates of the DLRF model on these two datasets are 0.906 8 and 0.996 8 respectively

and the F1-score are 0.906 8 and 0.996 0.

关键词

Keywords

references

谢添丞 , 吴凌淳 , 林羽丰 , 等 . 面向大数据的网络流量监控与分析算法综述 [J ] . 无线电通信技术 , 2022 , 48 ( 5 ): 782 - 793 .

XIE T C , WU L C , LIN Y F , et al . Survey of network traffic monitoring and analysis for big data [J ] . Radio Communications Technology , 2022 , 48 ( 5 ): 782 - 793 .

张涛 , 费稼轩 , 王琦 , 等 . 电力信息物理系统跨域攻击协同防御架构及机制研究 [J ] . 电子学报 , 2024 , 52 ( 4 ): 1205 - 1218 .

ZHANG T , FEI J X , WANG Q , et al . Research of architecture and mechanism of coordinative defense methods for cross-domain attacks of cyber physical system [J ] . Acta Electronica Sinica , 2024 , 52 ( 4 ): 1205 - 1218 .

董卫魏 , 王曦 , 钟昕辉 , 等 . 基于人工智能技术的轻量级网络入侵检测系统设计 [J ] . 现代电子技术 , 2024 , 47 ( 5 ): 108 - 111 .

DONG W W , WANG X , ZHONG X H , et al . Design of lightweight network intrusion detection system based on artificial intelligence technology [J ] . Modern Electronics Technique , 2024 , 47 ( 5 ): 108 - 111 .

KWON D , KIM H , KIM J , et al . A survey of deep learning-based network anomaly detection [J ] . Cluster Computing , 2019 , 22 ( 1 ): 949 - 961 .

AHMAD J , FARMAN H , JAN Z . Deep learning methods and applications [J ] . Springer Briefs in Computer Science , 2018 : 31 - 42 .

HU R , WU Z Y , XU Y , et al . Multi-attack and multi-classification intrusion detection for vehicle-mounted networks based on mosaic-coded convolutional neural network [J ] . Scientific Reports , 2022 , 12 ( 1 ): 6295 .

李安琪 , 杨琳 , 蔡言颜 , 等 . 基于递归特征消除-随机森林模型的江浙沪农田土壤肥力属性制图 [J ] . 地理科学 , 2024 , 44 ( 1 ): 168 - 178 .

LI A Q , YANG L , CAI Y Y , et al . Digital mapping of soil fertility attributes in croplands in Jiangsu, Zhejiang and Shanghai based on recursive feature elimination-random forest model [J ] . Scientia Geographica Sinica , 2024 , 44 ( 1 ): 168 - 178 .

罗红郊 , 马晓琴 , 孙妍 , 等 . 基于RFE特征选择的PSO-SVM用电量预测算法 [J ] . 电子设计工程 , 2023 , 31 ( 20 ): 172 - 176 .

LUO H J , MA X Q , SUN Y , et al . PSO-SVM electricity consumption prediction algorithm based on RFE feature selection [J ] . Electronic Design Engineering , 2023 , 31 ( 20 ): 172 - 176 .

李淑琪 , 光彪 , 赵玉凤 , 等 . SMOTE＿ENN结合AdaBoost在临床预测模型中的应用探析 [J ] . 中国卫生统计 , 2023 , 40 ( 6 ): 817 - 821 .

LI S Q , GUANG B , ZHAO Y F , et al . Application of SMOTE＿ENN combined with AdaBoost in clinical prediction model [J ] . Chinese Journal of Health Statistics , 2023 , 40 ( 6 ): 817 - 821 .

高鑫泽 , 吕国 , 杨宵 , 等 . 基于CNN-LSTM模型的入侵检测算法研究 [J ] . 河北建筑工程学院学报 , 2024 , 42 ( 3 ): 216 - 221 .

GAO X Z , LYU G , YANG X , et al . Research on intrusion detection algorithm based on CNN-LSTM model [J ] . Journal of Hebei Institute of Architecture and Civil Engineering , 2024 , 42 ( 3 ): 216 - 221 .

YANG S D , YU X Y , ZHOU Y . LSTM and GRU neural network performance comparison study: taking Yelp review dataset as an example [C ] // Proceedings of the 2020 International Workshop on Electronic Communication and Artificial Intelligence (IWECAI) . Piscataway : IEEE Press , 2020 : 98 - 101 .

BELLA H K , VASUNDRA S . A novel framework based on extra tree regression classifier and grid search LSTM for intrusion detection in IoT and cloud environment [J ] . International Journal of Intelligent Engineering and Systems , 2024 , 17 ( 4 ): 504 - 517 .

孙玉芹 , 王敏 , 田方 , 等 . 基于熵权法Stacking集成学习的多分类窃电检测 [J ] . 科学技术与工程 , 2024 , 24 ( 30 ): 12996 - 13004 .

SUN Y Q , WANG M , TIAN F , et al . Stacking integrated learning of multi-classification electricity theft detection based on entropy weight method [J ] . Science Technology and Engineering , 2024 , 24 ( 30 ): 12996 - 13004 .

梅元清 , 郭肇强 , 周慧聪 , 等 . 面向对象软件度量阈值的确定方法: 问题、进展与挑战 [J ] . 软件学报 , 2023 , 34 ( 1 ): 50 - 102 .

MEI Y Q , GUO Z Q , ZHOU H C , et al . Deriving object-oriented metric thresholds: research problems, progress, and challenges [J ] . Journal of Software , 2023 , 34 ( 1 ): 50 - 102 .

DAS S , SAHA S , PRIYOTI A T , et al . Network intrusion detection and comparative analysis using ensemble machine learning and feature selection [J ] . IEEE Transactions on Network and Service Management , 2022 , 19 ( 4 ): 4821 - 4833 .

ALEESA A M , YOUNIS M , MOHAMMED A A , et al . Deep-intrusion detection system with enhanced UNSW-NB15 dataset based on deep learning techniques [J ] . Journal of Engineering Science and Technology , 2021 , 16 ( 1 ): 711 - 727 .

YU X , LU Y , JIANG F , et al . A cross-domain intrusion detection method based on nonlinear augmented explicit features [J ] . IEEE Transactions on Network and Service Management , 2024 ( 99 ): 1 .

HENRY A , GAUTAM S . Intrusion detection using big data and deep learning techniques [C ] // Proceedings of the Computing, Communication and Learning: First International Conference . Waranga : Springer , 2023 : 220 - 230 .

ATTIQUE D , HAO W , PING W , et al . Explainable and data-efficient deep learning for enhanced attack detection in IIoT ecosystem [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 24 ): 38976 - 38986 .

浏览量

553

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

结合自适应数据增强和集成学习的机载网络入侵检测研究

基于LLM-RFE-XGBoost方法的客户升级投诉预警研究

基于GPT网络的日志文本故障关联规则挖掘研究

基于SDL-YOLO的红外图像人车检测算法

水声通信物理层技术综述：从模型驱动到数据驱动