[1]蔡宇航,廖光忠.基于改进降噪自编码模型的网络入侵检测[J].计算机技术与发展,2023,33(02):119-124.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 018]
　CAI Yu-hang,LIAO Guang-zhong.Network Intrusion Detection Based on Improved Denoising Autoencoder Model[J].,2023,33(02):119-124.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 018]
点击复制

基于改进降噪自编码模型的网络入侵检测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年02期
页码:
119-124
栏目:
网络空间安全
出版日期:
2023-02-10

文章信息/Info

Title:
Network Intrusion Detection Based on Improved Denoising Autoencoder Model
文章编号:
1673-629X(2023)02-0119-06
作者:
蔡宇航1 ; 廖光忠2
1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065;
2. 武汉科技大学 智能信息处理与实时工业系统湖北省重点实验室,湖北 武汉 430065
Author(s):
CAI Yu-hang1 ; LIAO Guang-zhong2
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;
2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System,Wuhan University of Science and Technology,Wuhan 430065,China
关键词:
网络入侵检测; 样本不平衡; 生成式对抗网络; 降噪自编码器; 门控循环单元
Keywords:
network intrusion detection; sample imbalance; generative adversarial network; denoising autoencoder; gated recurrent unit
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 02. 018
摘要:
针对网络入侵数据中样本不平衡现象导致多分类准确率普遍不高的问题,提出一种基于改进降噪自编码模型的网络入侵检测方法。 在数据处理方面,对原始网络入侵数据进行数值化和归一化预处理,并且使用生成对抗网络模型来对现有入侵数据进行数据增强,从而扩充少数类样本。 在入侵检测方面,对传统的降噪自编码器模型进行改进,通过在编解码网络中引用门控循环单元结构,使得该模型在具有一定的鲁棒性的同时,也保证了网络入侵数据的时序信息传递的连贯性,避免了重要数据特征的遗漏。 使用 UBSW-NB15 数据集对所提方法进行有效性验证,实验结果表明,与决策树、随机森林、GRU-RNN 等传统方法相比,所提方法在攻击类型少数类上的检测率明显提高,并且整体的检测性能更好。
Abstract:
A network intrusion detection method based on an improved denoising autoencoder model is proposed for the problem ofgenerally low accuracy of multi-classification due to the phenomenon of sample imbalance in network intrusion data. In terms of dataprocessing,the original network intrusion data is preprocessed numerically and normalized,and the existing intrusion data is augmentedusing a generative adversarial network model to expand the minority class samples. In terms of intrusion detection, the traditionaldenoising autoencoder model is improved by invoking a gated recurrent unit structure in the codec network,which makes the model robustwhile ensuring the coherence of the temporal information transfer of network intrusion data and avoiding the omission of important datafeatures. The effectiveness of the proposed method is verified using the UBSW-NB15 dataset,and the experimental results show that theproposed method can achieve a significant improvement in the detection rate of a few classes of attack types compared with traditionalmethods such as decision trees,random forests,and GRU-RNN,and the overall detection performance is excellent.

相似文献/References:

[1]李兵.一种基于对等模型的网络入侵检测系统模型[J].计算机技术与发展,2008,(03):173.
　LI Bing.A Distributed Intrusion Detection System Based on Peer - to - Peer Model[J].,2008,(02):173.
[2]吴楠 宋方敏.用C4．5算法对局域网数据报进行行为分类[J].计算机技术与发展,2006,(07):1.
　WU Nan,SONG Fang-min.Classify Datagram on LANs by Using C4.5 Classification Algorithm[J].,2006,(02):1.
[3]伍海波,高劲松,唐启涛,等.基于生物免疫原理的网络入侵检测研究[J].计算机技术与发展,2013,(07):167.
　WU Hai-bo[],GAO Jing-song[],TANG Qi-tao[],et al.Research on Network Intrusion Detection System Based on Biological Immune Principle[J].,2013,(02):167.
[4]贾慧敏. 基于ML改进技术的IDS的设计与实现[J].计算机技术与发展,2015,25(06):114.
　JIA Hui-min. Design and Implementation of IDS Based on ML’ s Improved Technology[J].,2015,25(02):114.
[5]马浩良,谢林柏.基于 SSD 的不平衡样本车辆检测与识别[J].计算机技术与发展,2019,29(12):135.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 024]
　MA Hao-liang,XIE Lin-bo.Vehicle Detection and Recognition in Unbalanced Samples Based on SSD[J].,2019,29(02):135.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 024]
[6]徐胜超,宋 娟,潘 欢.基于 MapReduce 并行关联挖掘的网络入侵检测[J].计算机技术与发展,2021,31(06):123.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 022]
　XU Sheng-chao,SONG Juan,PAN Huan.Network Intrusion Detection Based on Parallel AssociationMining of MapReduce[J].,2021,31(02):123.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 022]
[7]薛 飞,梁 栋,喻 洋.难例挖掘在太赫兹成像目标检测中的应用[J].计算机技术与发展,2021,31(09):124.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 021]
　XUE Fei,LIANG Dong,YU Yang.Application of Hard Example Mining to Terahertz Imaging Object Detection[J].,2021,31(02):124.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 021]
[8]张 凡*,高仲合,牛 琨.基于 BiGRU-SVM 的网络入侵检测模型[J].计算机技术与发展,2023,33(01):144.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 022]
　ZHANG Fan*,GAO Zhong-he,NIU Kun.Network Intrusion Detection Model Based on BiGRU-SVM[J].,2023,33(02):144.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 022]

更新日期/Last Update: 2023-02-10