基于马尔科夫聚类的通信网络敏感信息监测

Automatic monitoring method of sensitive information in communication network based on Markov clustering

通信网络敏感信息自动监测是识别网络异常行为的关键所在。针对目前方法难以有效区分通信网络异常行为与正常行为之间关系的问题,提出了一种基于马尔科夫聚类的网络敏感信息自动监测方法。该方法首先基于网络流信息构建邻接矩阵,然后利用马尔科夫聚类。利用聚类前后簇数和核心结构节点数目的变化特征,自动监测通信网络的敏感信息。实验结果表明,该方法能够有效监测出通信网络的敏感信息,且具有较高的识别准确率。

Automatic monitoring of sensitive information in communication network is the key to identify abnormal network behavior. Aiming at the problem that it is difficult to distinguish the relationship between abnormal behavior and normal behavior of communication network effectively by current methods,an automatic monitoring method of network sensitive information based on Markov clustering is proposed. This method first constructs the adjacency matrix based on network flow information,and then uses Markov clustering. The sensitive information of communication network is automatically monitored by using the changing characteristics of cluster number and core structure node number before and after clustering. The experimental results show that the method can effectively monitor the sensitive information of the communication network,and has high recognition accuracy.