摘要
针对传统模糊特征检测方法存在的效率低、精度不高等问题,设计了一种新的网络安全防护态势优化模型;对网络安全状态分布进行建模,并利用数据挖掘技术对网络信息进行挖掘;利用新型入侵识别检测方法对所设计的网络安全估计状态进行自适应特征提取,提取网络安全状况的特征数据集和处理单元;采用模糊C平均数据聚类方法(FCM)提取综合信息;对入侵特征信息流进行分类,根据属性分类结果进行网络安全态势预测,实现安全态势评估;基于不同场景下进行实验,结果表明,所提算法适用于网络安全的场景,准确性和鲁棒性都得到了验证。
Aiming at the problems of low efficiency and low accuracy of traditional fuzzy feature detection methods,a new network security protection situation optimization model is designed.The distribution of network security state is modeled,and the data mining technology is used to mine network information.The new intrusion identification detection method is used to extract adaptive features from the designed network security estimation state,and extract the characteristic data set and processing unit of network security state.Fuzzy C mean data clustering method(FCM)is used to extract the comprehensive information.The intrusion characteristic information flow is classified,and the network security situation is predicted according to the attribute classification results,and the security situation evaluation is realized.Based on the experiments in different scenarios,the results show that the proposed algorithm is suitable for network security scenarios,and its accuracy and robustness are verified.
作者
李星
李浩然
LI Xing;LI Haoran(Characteristic Medical Center of Chinese People s Armed Police Force,Information Centre,Tianjin 300162,China;Tianjin Institute of Industrial Biotechnology,Chinese Academy of Sciences,Tianjin 300308,China)
出处
《计算机测量与控制》
2023年第9期267-273,共7页
Computer Measurement &Control
关键词
数据聚类
网络安全防护
预测
数据挖掘
data clustering
network security protection
prediction
data mining
