摘要
研究保护网络安全问题,网络入侵具有多样性、不确定性和隐蔽性,由于安全检测易出现误检和漏检,对未知入侵行为无法正确检测,导致网络入侵检测困难,检测的正确率较低。为了提高网络入侵检测正确率,更好保护网络安全,提出基于关联规则的网络入侵检测方法。通过关联规则首先对网络用户正常行为进行挖掘,找出那些可信的并具有代表性的规则,然后利用关联规则对待用户行为进行检测。利用KDD CUP99数据集进行仿真,仿真结果表明,关联规则的入侵检测方法加快了检测速度,提高了网络入侵检测正确率,降低漏报率与误报率,可为网络保护设计提供参考。
Study on network security protection,network intrusion has diversity,uncertainty and concealment,because safety detection is easily mistaken and missed,unknown intrusion behavior cannot be detected correctly to detection accuracy is relatively low.In order to improve the network intrusion detection rate,protect network security better,this paper proposed a network intrusion detection method based on the association rules.Firstly,the network user normal behavior is mined by association rule to find the credible and representative rules,and then using association rules to detect user behavior.The simulation experiment is carried out on KDD CUP99 data set,the simulation results show that the proposed method can accelerate the detection speed and improve the network intrusion detection rate,reduce the false negative rate and false alarm rate,can offer the reference for the design of network protection.
出处
《计算机仿真》
CSCD
北大核心
2011年第11期130-133,共4页
Computer Simulation
基金
四川省教育厅自然科学重点科研项目(09ZA055)
关键词
数据挖掘
关联规则
入侵检测
网络入侵
Data mining
Association rule
Intrusion detection
Network intrusion
