云计算环境下的联合网络入侵检测方法仿真

发布时间：2018-12-14 12:43

【摘要】：在云计算环境下的联合网络中,各个层次网络受到入侵时,用于判断的入侵规则中,由于受到网络差异性的影响,会出现不相关联规,相似入侵规则下的不同层次网络交汇处也会出现一个阀值对应两种规则的"尖锐边界"问题。传统的网络入侵检测方法,对于不相干规则和边界阀值尖锐突变问题无法用一个或者多个固定数值表示,产生较大的误差。提出采用模糊C均值聚类算法的云计算环境下联合网络深度入侵检测方法。在不同层网络的连接边缘区域,根据关联的数据进行样本剖析,运用模糊C均值聚类方法将各层次的数据深入归纳运算,在归纳后的结果中获得异常数据所表现的规律,根据各种异常数据的行为规律结果进行不同层网络的入侵判定。仿真结果表明,利用改进算法进行不同层次的网络深度入侵检测,能够提高检测准确率,降低误报率。
[Abstract]:In the United network in cloud computing environment, when the network at all levels is invaded, the rules used to judge the intrusion will appear because of the influence of the network differences. There is also a "sharp boundary" problem where the threshold values correspond to two kinds of rules at the intersection of different levels of networks under similar intrusion rules. Traditional network intrusion detection methods can not be represented by one or more fixed numerical values for incoherent rules and sharp abrupt change of boundary thresholds, resulting in large errors. In this paper, a fuzzy C-means clustering algorithm is proposed to detect the depth of intrusion in cloud computing environment. In the connection edge area of different layers of network, the sample analysis is carried out according to the associated data, and the fuzzy C-means clustering method is used to induce the data of each level deeply, and the law of abnormal data is obtained in the result of induction. The intrusion detection of different layers of networks is carried out according to the behavior rules of various abnormal data. The simulation results show that the improved algorithm can improve the detection accuracy and reduce the false alarm rate.
【作者单位】：长春工业大学人文信息学院;
【基金】：吉林省教育厅“十二五”科学技术研究项目吉教科合子(【2013】第645号)
【分类号】：TP393.08

【参考文献】