【摘要】 通过对P2P应用的长期研究,根据P2P节点自身的特点选取了其中典型的特征属性,并提出了一种基于决策树模型的P2P节点识别方法。由于该方法是统计分析传输层数据分组的特征,因此对于采用加密或非加密的P2P应用的网络节点识别均有效。通过实验验证,与基于端口和基于负载特征的流量监测方法相比,所提出的方法体现出了较高的准确率和较低的漏报率及误报率。更多还原

【Abstract】 A P2 P nodes detection method based on decision model was proposed by a long time of observation. As this method is a statistical analysis of the transport layer packet characteristics, identification of the network node for encrypted or unencrypted P2 P applications is effective. Experiment shows that this method has higher accuracy and lower false positive rate and false negative rate.更多还原