电信科学 ›› 2015, Vol. 31 ›› Issue (6): 79-85.doi: 10.11959/j.issn.1000-0801.2015085

• 研究与开发 • 上一篇    下一篇

一种基于不均衡数据的网络入侵流量分类方法

关晓惠1,钱亚冠2   

  1. 1 浙江水利水电学院 杭州 310018
    2 浙江科技学院理学院 杭州 310023
  • 出版日期:2015-07-23 发布日期:2015-08-03
  • 基金资助:
    浙江省水利厅科技计划基金资助项目;浙江省网络媒体云处理与分析工程技术中心开放课题基金资助项目;2014年度高校国内访问学者专业发展基金资助项目

A Network Traffic Classification Method for Class-Imbalanced Data

Xiaohui Guan1,Yaguan Qian2   

  1. 1 Zhejiang University of Water Resources and Electric Power,Hangzhou 310018,China
    2 College of Science,Zhejiang University of Science and Technology,Hangzhou 310023,China
  • Online:2015-07-23 Published:2015-08-03
  • Supported by:
    Water Resources Department Foundation of Zhejiang Province;The Open Project of Cloud Processing and Analysis Center of Network Media of Zhejiang Province;The Professional Development Project of 2014 College Visiting Scholar

摘要:

在网络入侵流量检测中,普遍存在不同攻击类型的流量分布不均现象,导致少数攻击流量类识别率较低。为解决此类问题,基于不同特征空间的分类器流水线组合方法将多分类问题转化为不同特征空间上的两分类问题,有效地实现少数类重抽样和特征空间的优化,避免了少数类受多数类特征的干扰。实验表明,此方法可以有效地提高攻击流量中少数类的分类精度和召回率。

关键词: 攻击流量, 类不均衡, 分类器流水线组合

Abstract:

It is very common that flow distribution of class is not uniform in attack traffic. It wi11 lead to a 1ow classification accuracy in network intrusion detection. For overcoming this class imbalance phenomenon,a pipelining ensemble approach in different feature spaces was proposed,which translates multi-class classification to two-class classification. Based on the pipelining ensemble,it could be further conduct oversampling and customized feature selection for minority class,which may avoid the disturbance from majority class. The experiment result shows that the proposed approach can efficiently improve the accuracy of minority class of attack traffic.

Key words: attack traffic, class imbalance, classifiers pipelining ensemble

No Suggested Reading articles found!