熵权神经网络的信息系统安全评估  

Information system security evaluation based on entropy weight method and neural network

作　　者：顾兆军[1,2] 辛倩 GU Zhao-jun 1,2 ,XIN Qian 1,2(1.Information Security Evaluation Center,Civil Aviation University of China,Tianjin 300300,China;2.College of Computer Science and Technology,Civil Aviation University of China,Tianjin 300300,Chin)

机构地区：[1]中国民航大学信息安全测评中心,天津300300 [2]中国民航大学计算机科学与技术学院,天津300300

出　　处：《计算机工程与设计》2018年第7期1856-1860,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(61601467;U1533104);民航科技基金项目(MHRD20140205;MHRD20150233);民航安全能力建设基金项目(PDSA008);中央高校基本科研业务费中国民航大学专项基金项目(3122013Z008;3122013C004;3122015D025)

摘　　要：为提高信息系统安全评估的准确性,提出一种基于熵权法的BP神经网络评估模型。采用熵权法对安全指标体系进行处理,提取重要指标,剔除对评估结果无影响的指标,将重要指标作为BP神经网络的输入,提高BP神经网络对知识的学习能力,利用实例验证模型的性能。验证结果表明,与其它同类型评估模型相比,熵权-BP模型训练速度快,评估精度高,可以为信息系统管理员提供科学的参考依据。To improve the accuracy of information system security evaluation,a BP neural network evaluation model based on entropy weight method was proposed.The entropy method was used to deal with the safety index system to extract the important indexes and eliminate the indexes with no impact on the evaluation results.The important indexes were taken as the input of BP neural network to improve the learning ability of BP neural network,and the performance of this model was verified in the end.The results show that compared with other similar types of evaluation models,the evaluation accuracy and the speed of entropy weight-BP model are higher.The method can provide a scientific reference for information system administrators.

关 键 词：信息系统安全 熵权法 神经网络 评估模型 非线性 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]