基于Transformer神经网络模型的网络入侵检测方法
CSTR:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

国家电网有限公司总部科技项目资助(5700-202024193A-0-0-00)。


Network intrusion detection method based on Transformer neural network model
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    网络入侵检测一直以来都是网络安全中亟待解决的关键任务之一,传统网络入侵检测方法主要通过提取多维特征,采用机器学习方法构建检测模型,大多忽略了入侵行为的时间相关性。通过提取网络入侵行为的时序特征,设计基于降维特征的多头自注意力机制Transformer网络模型,以解决传统串行化时序神经网络模型不易收敛且时间开销较大的问题,通过选取最优的损失函数和训练参数进行并行化训练,实现网络入侵行为检测。实验结果表明,基于Transformer网络模型的网络入侵检测方法在多个数据集上均获得了99%以上的精度和检出率。

    Abstract:

    Network intrusion detection has always been one of the key tasks in network security. Traditional network intrusion detection methods mainly use machine learning method to construct detection models by extracting multi-dimensional features, while most of them ignore the time correlation of intrusion behaviors. In this paper, a Transformer network model with multi-head self-attention mechanism based on dimension reduction feature was designed by extracting the time sequence features of network intrusion behavior. The proposed model solved the problems that traditional serial sequential neural network models are difficult to converge and have a large time consumption. The optimal loss function and training parameters were selected to implement the network intrusion detection. The experimental results show that the network intrusion detection method based on Transformer network model achieves the accuracy and the detection rate of over 99% in multiple datasets.

    参考文献
    相似文献
    引证文献
引用本文

郭志民,周劼英,王丹,吕卓,杨文.基于Transformer神经网络模型的网络入侵检测方法[J].重庆大学学报,2021,44(11):81-88.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-05-18
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2021-12-02
  • 出版日期:
文章二维码