基于信息熵和K均值的船舶网络入侵检测方法  

Research on Ship Network Intrusion Detection Based on Information Entropy and K-means Algorithm

作　　者：肖鹏博 闵绍荣[1] 罗威[1] XIAO Peng-bo;MIN Shao-rong;LUO Wei(China Ship Development and Design Center,Wuhan 430064)

机构地区：[1]中国舰船研究设计中心

出　　处：《软件》2019年第9期36-39,共4页Software

基　　金：国防基础科研计划资助,项目编号JCKY2018207C121

摘　　要：船舶网络是维护船舶正常功能的重要结构,当船舶网络被入侵时,网络流量会呈现异常状态,严重影响船舶功能。而当前的船舶网络入侵检测方法不能兼顾检测速度和准确度,无法满足入侵检测要求。为了克服目前船舶网络入侵检测方法存在的不足,以改善船舶入侵检测方法的性能,提出基于信息熵和K均值算法的船舶网络入侵检测方法,通过信息熵理论找到最优特征子集,然后利用K均值算法实现入侵检测,并与普通K均值算法进行对比测试。结果表明:本文方法可以有效检测出船舶网络入侵状况,并且在保证准确性的同时极大的缩短了检测时间,是一种高效的入侵检测方法。Ship network is an important structure to maintain the normal function of ships.When the ship network is intruded,the network flow will be abnormal,which will seriously affect the ship function.However,the current methods of ship network intrusion detection can not give consideration to both detection speed and accuracy,and can not meet the requirements of intrusion detection.In order to overcome the current ship the deficiency existing in network intrusion detection methods,to improve the performance of ship's intrusion detection method,based on information entropy and shipping network intrusion detection method of k-means algorithm,through the information entropy theory to find the optimal data subset,then using k-means algorithm to detect network intrusion,and compared with ordinary k-means algorithm.The results show that this method can effectively detect the ship network intrusion,and not only ensure the accuracy but also greatly shorten the detection time,It is an efficient intrusion detection method.

关 键 词：船舶网络 入侵检测 信息熵 聚类算法 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]