首页> 外文会议>International Conference on Smart City and Systems Engineering >Network Anomaly Traffic Detection Method Based on Support Vector Machine
【24h】

Network Anomaly Traffic Detection Method Based on Support Vector Machine

机译:基于支持向量机的网络异常交通检测方法

获取原文

摘要

Network traffic is the amount of data moving across a network at a specific time, and anomaly traffic detection is of great importance in computer networks. In this paper, we integrate the entropy theory and support vector machine to detect Network anomaly traffic. We utilize the entropy theory to establish the network traffic feature vector using the entropy theory, and then exploit the support vector machine to detect the network anomaly traffic by tackling a classification problem. Particularly, six types of network features are used to construct feature vector in this work, such as Source IP, Destination IP, Source Port, Destination Port, Packet Size and Packet Type. Afterwards, we provide the network feature vector to SVM to learn network traffic behaviors. Experimental results demonstrate that compared with existing method, our proposed method can detect network anomaly traffic with high accuracy.
机译:网络流量是在特定时间跨网络移动的数据量,并且在计算机网络中的异常流量检测非常重要。在本文中,我们整合了熵理论并支持向量机来检测网络异常流量。我们利用熵理论使用熵理论来建立网络流量特征向量,然后利用支持向量机通过解决分类问题来检测网络异常流量。特别地,六种类型的网络特征用于构建本工作中的特征向量,例如源IP,目标IP,源端口,目标端口,数据包大小和数据包类型。之后,我们将网络功能向量提供给SVM以学习网络流量行为。实验结果表明,与现有方法相比,我们所提出的方法可以以高精度检测网络异常流量。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号