<-上一篇/Previous Article 下一篇/Next Article->

[1]万月亮,朱贺军,刘宏志.流特征的Skype流量识别[J].智能系统学报,2010,5(2):139-143.
　WAN Yue-liang,ZHU He-jun,LIU Hong-zhi.Skype traffic identification based on flow characteristics[J].CAAI Transactions on Intelligent Systems,2010,5(2):139-143.

点击复制

流特征的Skype流量识别

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 5 期数: 2010年第2期页码: 139-143 栏目: 学术论文—机器感知与模式识别出版日期: 2010-04-25

Title:: Skype traffic identification based on flow characteristics

文章编号:: 1673-4785(2010)02-0139-05

作者:: 万月亮¹,朱贺军^2,刘宏志^1; 1.北京工商大学计算机与信息工程学院，北京 100048;
2. 公安部第三研究所北京锐安科技有限公司，北京 100044

Author(s):: WAN Yue-liang¹， ZHU He-jun²， LIU Hong-zhi^1; 1.College of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China; 2. The Third Research Institute of Ministry of Public Security Run Technologies Co.,Ltd. ，Beijing 100044, China

关键词:: 流量识别; 朴素贝叶斯分类; 深度包检测; 实时流特征

Keywords:: traffic identification; naive Bayesian classification; deep packet inspection; realtime flow characteristic

分类号:: TP393

文献标志码:: A

摘要:: Skype流识别的研究大多局限于在静态载荷特征和通信机制，没有考虑网络流特征在Skype流量识别中的作用.提出了一种基于朴素贝叶斯分类的Skype流量识别模型.选择流的连接特征和实时特征作为分类特征集，根据流的连接特征组织网络流，再进一步根据流的包长度、平均发送间隔和突发带宽消耗等实时流特征识别Skype流量.在北京联通骨干网络上的实验表明该模型能有效地识别Skype流，是一种有效的Skype流识别算法.

Abstract:: Most of the Skype traffic identification models are limited to Skype communication mechanisms and static payload characteristics. No net flow characteristics are considered in identification algorithms. To overcome this limitation, a hierarchical Skype traffic identification model based on naive Bayesian classification was developed. Flows were analyzed according to network connection modes. Results were then obtained according to realtime flow characteristics, such as packet size, average interpacket gap and burstiness of bandwidth consumption. The validity of the algorithm was proven by testing conducted on the Beijing China Unicom backbone network.

参考文献/References:: ［1］BASET S A, SCHULZRINNE H. An analysis of the Skype peertopeer internet telephony protocol［C］// IEEE Infocom’06. Barcelona, Spain, 2006：111.
［2］BIONDI P, DESCLAUX F. Silver needle in the Skype［C］//Black Hat Europe’06. Amsterdam, The Netherlands, 2006, 1:2547.
?［3］YU Y F, LIU D D, LI J, et al. Traffic identification and overlay measurement of Skype［C］//Proc of IEEE International Conference on Computational Intelligence and Security. Guangzhou, China, 2006： 10431048.
［4］CHEN K T, HUANG C Y, HUANG P, et al. Quantifying fying Skype user sattsfaction［C］//ACM SIGCOMM’06. Pisa, Italy, 2006：399410.
［5］LU L, JEFFREY H, SAFAVINAINII R, et al. Transport layer identification of Skype traffic［C］//ICOIN 2007. Estoril, Portugal, 2007：465481.
［6］DARIO B, MARCO M, MICHELA M. Revealing Skype traffic when randomness plays with you［C］//ACM Sigcomm’07. Kyoto, Japan, 2006:3748.
［7］FALOUTSOS M, KARAGIANNIS C K, BROIDO A T. Transport layer identification of P2P traffic［C］// Proceedings of the 4th ACM SIGCOMM Conference on Internet Measurement. Taormina, Sicily, Italy, 2004: 121134.
［8］MOORE A，ZUEV D. Internet raffic classification using Bayesian analysis［C］//ACM Sigmetrics BANFF, CA, 2005：5060
［9］FENG W, CHANG F, FENG W, et al. A traffic characterization of popular online games［J］. IEEE/ACM Transactions on Networking，2005,13(3): 488500.

备注/Memo

收稿日期：2009-12-27.
通信作者：万月亮.E-mail:yueliang_wan@126.com
万月亮，男，1973年生，讲师，博士，主要研究方向为网络信息安全、海量数据挖掘、网络行为分析、网络视频挖掘.发表学术论文近10篇，出版编著1部.
朱贺军，男，1973年生，硕士，主要研究方向为网络信息安全、互联网挖掘与数据挖掘.
?刘宏志，男，1964年生，教授，博士，主要研究方向为信息工程监理与电子政务、软件工程、计算机网络，发表学术论文60余篇，主编、参编论著及教材10余部

更新日期/Last Update: 2010-05-24

流特征的Skype流量识别 PDF下载HTML

备注/Memo

流特征的Skype流量识别

PDF下载 HTML