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 ›› 2011, Vol. 37 ›› Issue (6): 256-259. doi: 10.3969/j.issn.1000-3428.2011.06.089

• 开发研究与设计技术 • 上一篇    下一篇

IPTV平台实时检测系统的设计与实现

何 杰 1a ,刘朝斌 2,杨岳湘 1a,唐 川 1b   

  1. (1. 国防科学技术大学 a. 计算机学院;b. 信息中心,长沙 410073;2. 第二军医大学信息中心,上海 200433)
  • 出版日期:2011-03-20 发布日期:2011-03-29
  • 作者简介:何 杰(1984-),男,硕士研究生,主研方向:网络安全;刘朝斌,硕士;杨岳湘,教授、博士生导师;唐 川,工程师
  • 基金资助:
    国家“863”计划基金资助重点项目(2008AA01Z407);湖南省自然科学基金资助项目(07JJ5084);广东省科技计划基金资助项目(2009B080701031)

Design and Implementation of IPTV Platform Real-time Detection System

HE Jie 1a, LIU Chao-bin 2, YANG Yue-xiang 1a, TANG Chuan 1b   

  1. (1a. School of Computer; 1b. Information Center, National University of Defense Technology, Changsha, 410073, China;2. Information Center, The Second Military Medical University, Shanghai, 200433, China)
  • Online:2011-03-20 Published:2011-03-29

摘要: 基于P2P的网络电视直播(IPTV)业务快速发展并带来诸多安全隐患,精确检测IPTV流使用的平台是对其实施有效监管的前提。为此,采用支持向量机方法,依据网络流量的流量特征和行为特征,选取PPlive、PPstream、QQlive、Sopcast和UUsee作为IPTV平台的代表,设计并实现一种IPTV平台实时检测系统。实验结果证明,该系统能够在5 min内检测出被管理节点是否在使用IPTV平台及平台类型,平均检测精度为90.62%。

关键词: 实时检测, P2P网络, IPTV业务, 支持向量机

Abstract: The rapid development of P2P based Internet Protocol Television(IPTV) has brought many potential security risks. The accurate detection of IPTV platform is the prerequisite for its effective supervision. In this paper, based on the flow features and behavior features of network traffic, by using support vector machine method, selecting PPlive, PPstream, QQlive, Sopcast and UUsee as representatives for IPTV platforms, it designs and implements an IPTV platform real-time detection system. Experiment results show the system can detect whether the managed node is using an IPTV platform, and it is with 90.62% correct rate within 5 minutes.

Key words: real-time detection, P2P network, IPTV service, Support Vector Machine(SVM)

中图分类号: