摘要
传统k-means聚类算法在预处理和K值确定等存在网络入侵行为检测效率低、检测准确性差、处理被动等问题。为解决上述问题,文章提出了一种改进后的k-means聚类算法网络安全检测模型,并借助数据集实现对模型的仿真实验。经仿真证明,提出的算法在网络入侵检测准确率与检测效率等方面均超过传统聚类算法,并进一步降低了网络异常检测误报率。
The conventional K-means clustering algorithm bears the shortcomings of low detection efficiency,poor detection accuracy and passive processing in the pre-processing and K value determination in face of network intrusion.In order to remove the above problems,an improved K-means clustering algorithm network security detection model is proposed in this paper,and it realizes the simulation experiment of the model with the help of data sets.The simulation results show that the proposed algorithm outperforms the conventional clustering algorithm in terms of accuracy and efficiency of network intrusion detection,and it further reduces the false alarm rate of detection against network anomaly.
作者
刘福刚
Liu Fugang(College of Information Engineering,Huainan Union University,Huainan,AnHui 232001)
出处
《绥化学院学报》
2023年第11期157-160,共4页
Journal of Suihua University
基金
安徽省高校自然科学研究重点项目“基于能距关系模型WSN多跳路由MRPGS算法研究”(KJ2021A1313)
作者简介
刘福刚(1980-),男,安徽颍上人,淮南联合大学信息工程学院讲师,硕士,研究方向:网络安全、数据挖掘、隐私保护。
