现代电子技术2025，Vol.48Issue(5)：101-106,6.DOI:10.16652/j.issn.1004-373x.2025.05.016
基于MIDBO-SVR的网络安全态势评估方法
Network security situation assessment method based on MIDBO-SVR
摘要
Abstract
The current network security situation assessment models have slow convergence speed and low accuracy,so a multi-strategy improved dung beetle optimization(MIDBO)algorithm is used to optimize the support vector regression(SVR)machine,and on the basis of the optimized SVR machine,a network security situation assessment model is established.The chaotic elite opposition-based learning(EOBL)strategy is used to initialize the dung beetle population,so as to enhance the diversity and quality of the population.A golden sine strategy with adaptive weight is adopted to update the position of the rolling dung beetle,so as to balance the local excavation ability and global search capability.The Lévy flight strategy is introduced to improve the position update formula of the thieving dung beetle,so as to enhance the algorithm's ability to escape from local optima.The position update method of whale optimization is referenced to improve the reproduction and foraging behavior,so as to increase the convergence speed and improve optimization accuracy of the algorithm.The MIDBO is used to optimize SVR machine,so as to obtain the optimal kernel function parameters and penalty factors.On the basis of the above,a network security situation assessment model based on MIDBO-SVR is constructed.Experimental results show that the assessment model based on MIDBO-SVR has higher classification accuracy and operational efficiency in comparison with the assessment models based on APSO-SVR,DBO-SVR and SVR.To sum up,the proposed model has the optimal comprehensive performance.关键词
网络安全/态势评估/多策略/DBO/支持向量回归机/自适应权重Key words
network security/situation assessment/multi-strategy/DBO/SVR machine/adaptive weight分类
信息技术与安全科学引用本文复制引用
陈秋琼,徐华志,熊伟男,刘卫丽..基于MIDBO-SVR的网络安全态势评估方法[J].现代电子技术,2025,48(5):101-106,6.基金项目
中国博士后科学基金项目(2015M572694,2016T90979) （2015M572694,2016T90979）
