基于粗糙加权平均单依赖估计的入侵检测算法

发布时间：2018-06-10 01:00

本文选题：入侵检测 + 粗糙集理论　；参考：《南京理工大学学报》2017年04期

【摘要】：入侵检测作为网络安全的重要方向,得到了越来越多的重视,大量传统的数据挖掘算法被尝试应用到入侵检测的数据分析领域。随着网络带宽不断提升,激增的数据量和类型繁多的协议格式使得这些传统算法在入侵检测方向的应用出现了识别精度差、运行效率不高或者参数选取困难等实际问题。该文提出一种基于粗糙集理论和贝叶斯理论的粗糙加权平均单依赖估计入侵检测算法,该方法基于粗糙集理论对网络数据进行属性约简,使用加权平均单依赖估计方法进行分类,完成对网络数据的入侵检测,算法资源消耗较低且易于实现。实验证明,该方法具有较好运行效率与准确度。
[Abstract]:As an important direction of network security, intrusion detection has received more and more attention. A large number of traditional data mining algorithms have been tried to be applied to the field of data analysis of intrusion detection. With the continuous improvement of network bandwidth, the large amount of data and various protocol formats make these traditional algorithms have some practical problems such as low recognition accuracy, low running efficiency or difficult parameter selection in the direction of intrusion detection. In this paper, a rough weighted average single dependency estimation intrusion detection algorithm based on rough set theory and Bayesian theory is proposed. The method of weighted average single dependency estimation is used to classify the intrusion detection of network data. The algorithm has low resource consumption and is easy to implement. Experimental results show that the method has good operation efficiency and accuracy.
【作者单位】：南京理工大学计算机科学与工程学院;中兴通讯股份有限公司南京研发中心;
【基金】：国家重点研发计划政府间国际科技创新合作重点专项(S2016G9070) 江苏省重大研发计划社会发展项目(BE2017739);江苏省重大研发计划产业前瞻项目(BE2017100) 中央高校基本科研业务费专项资金(30916015104) 赛尔下一代互联网创新项目(NGII20160122) 中兴通讯产学研合作论坛合作项目(2016ZTE04-11)
【分类号】：TP393.08

【相似文献】