作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 安全技术 • 上一篇    下一篇

基于主成分分析和学习矢量量化的会话初始协议识别研究

李进东,王韬,吴杨,雷东   

  1. (军械工程学院 信息工程系,石家庄 050003)
  • 收稿日期:2015-06-25 出版日期:2016-06-15 发布日期:2016-06-15
  • 作者简介:李进东(1990-),男,硕士研究生,主研方向为网络对抗、信息安全;王韬,教授、博士生导师;吴杨,博士研究生;雷东,硕士研究生。
  • 基金资助:
    国家自然科学基金资助项目“分组密码代数旁路攻击技术研究”(61173191)。

Research on Session Initiation Protocol Identification Based on Principal Component Analysis and Learning Vector Quantization

LI Jindong,WANG Tao,WU Yang,LEI Dong   

  1. (Deptarment of Information Engineering,Ordnance Engineering College,Shijiazhuang 050003,China)
  • Received:2015-06-25 Online:2016-06-15 Published:2016-06-15

摘要: 针对加密会话初始协议(SIP)识别困难以及相关研究工作较少,对入侵检测、网络流量监控等工作带来不便的问题,提出基于主成分分析(PCA)和学习矢量量化(LVQ)网络的SIP协议识别模型。通过对SIP协议的网络流特征进行PCA,提取出累计贡献率高于85%的相关流特征作为SIP协议识别过程中的主要特征,并进行LVQ网络训练,构建出完整的SIP协议识别模型。实验结果表明,PCA_LVQ模型对SIP协议的识别率均高于90%,通过PCA提取的SIP协议网络流属性区别于非SIP协议的属性,该模型对SIP协议的识别效果较好。

关键词: 会话初始协议, 主成分分析, 学习矢量量化, 特征值, 加密协议, 流特征

Abstract: The encrypted Session Initiation Protocol(SIP) is difficult to identify and there is less related research,which makes the intrusion detection and the network traffic monitoring inconvenient.Aiming at these problems,this paper proposes a SIP identification model based on Principal Component Analysis(PCA) and Learning Vector Quantization(LVQ) network.It extracts the feature of relevant flow characteristics,the cumulative contribution rate of which is higher than 85%,as the main characteristic during the identification of SIP by adopting PCA on the network traffic properties of the SIP.Then it trains the LVQ network training and builds a complete SIP identification model.Results show that the PCA_LVQ model can identify the SIP with a recognition rate higher than 90%,indicating that the property of SIP extracted by PCA network flow is different from non-SIP.The model has good effect on identifying SIP.

Key words: Session Initiation Protocol(SIP), Principal Component Analysis(PCA), Learning Vector Quantization(LVQ), eigen value, encrypted protocol, flow characteristic

中图分类号: