基于复杂网络社团划分的网络流量分类

随着网络的高速发展以及各种应用的不断涌现，采用端口号映射或有效负载分析的方法进行流量分类与应用识别已难以满足应用的需求。以流为网络节点、流之间统计特征的相似度为边，构建流相关网络模型，利用Newman快速社团划分算法(NFCD)对流相关网络模型进行社团划分，得到了流的聚类结果，实现了网络流量的分类，并与先前的两种无监督的流量分类算法(K-Means,DBSCAN)进行了对比。实验结果显示，利用NFCD算法具有更高的准确率，并能产生更好的聚类效果，且不受输入参数影响。

Internet Traffic Classification Based on Detecting Community Structure in Complex Network

In recent years, Internet traffic classification using port based or payload-based methods is becoming increasingly difficult with peer-to-peer(P2P) applications using dynamic port numbers,masquerading techniques, and encryption to avoid detection. Because supervised clustering algorithm needs accuracy of training sets and it can not classify unknown apphcation,we introduced complex network's community detecting algorithm,a new unsupervised classify algorithm, which has previously not been used for network traffic classification. We evaluated this algorithm and compared it with the previously used unsupervised K-means and DBSCAN algorithm, using empirical Internet traces. The experiment results show complex network's community detecting algorithm works very well in accuracy and produces better clusters, besides, complex network's community detecting algorithm need not know the number of the traffic application beforehand.