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。
关键词:
P2P网络,
协议栈,
统计特征,
神经网络
Abstract: 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 traffic. Experimental results show that this method has proper accuracy on P2P traffic identification.
Key words:
P2P network,
protocol stack,
statistic characteristic,
neural network
中图分类号:
李 鑫;刘东林. 基于统计特征的P2P流量检测方法[J]. 计算机工程, 2010, 36(5): 114-115.
LI Xin; LIU Dong-lin. P2P Traffic Detection Method Based on Statistical Characteristic[J]. Computer Engineering, 2010, 36(5): 114-115.