期刊文献+

一种基于MMTD网络异常流量的研究

A Study of Abnormal Network Traffic based MMTD
下载PDF
导出
摘要 当今的网络在设计初期并没有充分考虑其安全性,因此使得网络被频频攻击成功。当网络管理人员在检测网络是否遭到黑客的攻击时,可以从网络流量的角度出发,检测网络流量是否异常。网络流量是否异常可以作为网络是否被攻击的一个依据。网络中的流量存在正常还是异常的两种状态,在参考已有的检测技术之后,使用MMTD这一算法来检测网络的流量。在文中根据流与流量的特性给出检测函数y=f(x),最后使用MMTD这一算法进行流量是否异常做出判断。利用MMTD算法来研究网络的流量尚属第一次,该算法能够使得已有流量检测算法具有一定的智能性,可以作为已有流量检测算法的补充。 In today's network in the early stages of design and not ful y consider their safety, so that the network is frequently at ack success. When the network management personnel in detecting whether the network hacker at acks, can start from the network point of view, if the network traf ic anomaly detection. If the network traf ic anomaly can be regarded as a basis for the network is at acked. Flows in the network there are two types of normal or abnormal, after detection technology reference existing, the use of the MMTD algorithm to detect network traf ic. According to the characteristics of flow and flow detection function is given, and final y the use of the MMTD algorithm is used to judge whether the abnormal flow. To study the network using MMTD algorithm flow for the first time, the algorithm can make the existing traf ic detection algorithm has certain intel igence, can be used as a supplementary flow detection algorithm.
作者 朱俚治
出处 《信息安全与技术》 2014年第7期38-41,共4页
基金 北京航空航天大学软件开发环境国家重点实验室开放基金资助项(SKLSDE-2013KF)
关键词 MMTD 网络流量 报文 MMTD network traf ic message
  • 引文网络
  • 相关文献

参考文献4

二级参考文献40

  • 1马力,焦李成,董富强.一种Internet的网络用户行为分析方法的研究[J].微电子学与计算机,2005,22(7):124-126. 被引量:22
  • 2马维旻,李忠诚.基于流的网络流量特征分析[J].小型微型计算机系统,2005,26(9):1454-1458. 被引量:7
  • 3顾荣杰,晏蒲柳,邹涛.基于统计方法的骨干网异常流量建模与预警方法研究[J].计算机科学,2006,33(2):92-96. 被引量:3
  • 4陈宝钢,张凌,许勇,胡金龙,黄松.基于P2P应用的网络流量特征分析[J].计算机应用,2007,27(3):531-533. 被引量:7
  • 5MOORE A W,PAPAGIANNAKI K.Toward the accurate identification of network applications[C] //Proc.of the 6th International Workshop on Passive and Active Network Measurement.Heidelberg:Springer Verlag,2005:41-54.
  • 6LI Wei,CANINI M,MOORE A W.Efficient application identification and the temporal and spatial stability of classification schema[J].Computer Networks,2009,53(6):790-809.
  • 7CHOI K,CHOI K J.Pattern Matching of Packet Payload for Network Traffic Classification[C] //Proc.of the 1st International Conference on Next Generation Network (NGNCON 2006).Korea:Hyatt Regency Jeju,2006.
  • 8ZANDER S,NGUYEN T,ARMITAGE G.Automated Traffic Classification and Application Identification using Machine Learning[C] //Proc.of the IEEE Conference on Local Computer Networks 30th Anniversary,2005:250-257.
  • 9MOORE A W,ZUEV D.Internet traffic classification using Bayesian analysis techniques[C] //Proc.of ACM SIGMETRICS,New York:ACM Press,2005:50-60.
  • 10ERMAN J,MAHANTI A,ARLITT M,COHEN I.Offline/ realtime traffic classification using semi-supervised learning[J].Performance Evaluation,2007,64(9-12):1194-1213.

共引文献84

相关主题

;
使用帮助 返回顶部