基于统计特征的P2P流量检测方法  

P2P Traffic Detection Method Based on Statistical Characteristic

作　　者：李鑫[1] 刘东林[1] 

机构地区：[1]华东理工大学信息科学与工程学院,上海200237

出　　处：《计算机工程》2010年第5期114-115,共2页Computer Engineering

摘　　要：针对传统的流量检测方法在应对P2P流量时不够准确和高效的问题,分析P2P协议的TCP/IP协议栈,提出一种新的基于统计特征的P2P流量检测方法,结合神经网络对P2P流量进行识别。实验结果表明,该方法能有效、准确地判断网络数据流是否为P2P类别。With rapid development of P2P technology and its protocol complexity, traditional P2P traffic identification solution is not accurate and efficient. Aiming at this problem, this paper proposes a solution based on new P2P statistic characteristic and neural network to identify P2P truffle. Experimental results show that this method has proper accuracy on P2P trafffic identification.

关 键 词：P2P网络 协议栈 统计特征 神经网络 

分 类 号：TP393.03[自动化与计算机技术—计算机应用技术]