上海交通大学图像处理与模式识别研究所,上海,200240
网络首发:2009-02-10,
纸质出版:2009
移动端阅览
徐莉 1, 赵曦 2, 赵群飞 1, 等. 利用统计特征的网络应用协议识别方法[J]. 西安交通大学学报, 2009,43(2):43-47.
徐莉 1, 赵曦 2, 赵群飞 1, et al. Network Application Protocol Identification Based on Statistical Methods[J]. 2009, 43(2): 43-47.
在网络流统计特征的基础上
提出了一种应用协议识别算法.根据网络流概念
在网络层建立应用协议特征的描述方法
并采用数据量、数据包、时间3种属性全面地描述网络协议的特征.采用主成分分析方法来确定网络流特征属性的主要成分
以减少环境因素的影响.结合BP神经网络算法建立的网络协议识别模型
其网络特征具有良好的持久性和稳定性
模型分类结果也不易受网络环境的影响.真实网络环境下的实验结果显示
所提方法能够准确识别目前网络中常用的应用协议
包括HTTP、FTP、BitTorrent及TELNET
识别准确率达到了97%以上.
An application protocol identification method is proposed based on the statistical characteristics of network flows. The flow features at the network level are extracted according to the concept of network flow
and three attributes: the number of packets
the number of bytes
and time
are used to capture the flow characteristics roundly. Then the principal component analysis algorithm is used to determine the main characteristics of the flow attributes to reduce the effect of environment. Finally
a BP neural network model is given to identify the application protocols. As the features used in the proposed method are more stable
the output results of the model are hence accurate with the change of the network environment. Experimental results in real network environments show that the proposed method can identify several major application protocols accurately
such as HTTP
BitTorrent
FTP and TELNET
and the identification precision is above 97%.
MOORE D, KEYS K, KOGA R, et al. The CoralReef software suite as a tool for system and network administrators [C]∥Proceedings of the 15th USENIX Conference on Systems Administration. Berkeley, CA, USA: USENIX Association, 2001: 133-144.
ROESCH M. SNORT: lightweight intrusion detection for networks[C]∥Proceedings of the 13th USENIX Conference on Systems Administration. Berkeley, CA, USA: USENIX Association, 1999: 229-238.
ZUEV D, MOORE A W. Traffic classification using a statistical approach[C]∥6th International Workshop on Passive and Active Network Measurement. Berlin, Germany: Springer-Verlag, 2005: 321-324.
ERMAN J, ARLITT M, MAHANTI A. Traffic classification using clustering algorithms [C]∥Proceedings of ACM SIGCOMM Workshop on Mining Network Data. New York, USA: ACM,2006: 281-286.
王锐,王逸欣,樊爱华,等. 一种跨层P2P流量检测方法 [J]. 计算机应用, 2006,26(12):30-32.
WANG Rui, WANG Yixin, FAN Aihua, et al. A P2P traffic detection method between levels [J]. Computer Applications,2006,26(12):30-32.
CROTTI M, DUSI M, GRINGOLI F,et al. Traffic classification through simple statistical fingerprinting [C]∥Proceedings of ACM SIGCOMM Computer Communication Review. New York, USA: ACM,2007:5-16.
DUDA R O, HART P E, STORK D G. Pattern classification [M]. 2nd ed.Beijing, China: China Machine Press, 2004:576-580.
程洪, 郑南宁, 高振海,等.基于主元神经网络和K-均值的道路识别算法[J]. 西安交通大学学报, 2003,37(8): 812-815.
CHENG Hong, ZHENG Nanning, GAO Zhenhai,et al. Road recognition algorithm using principal component neural networks and K-means [J]. Journal of Xi'an Jiaotong University, 2003,37(8): 812-815.
HECHT-NIELSON R. Neuron computing [M]. Reading, MA, USA: Addsion Wesley,1990: 124-125.
0
浏览量
4
下载量
4
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621