一个基于神经网络的信息系统安全性综合评估模型

本文提出了一个将神经网络技术与模糊综合评价法结合的评估模型。首先根据信息系统资产的组成以及安全性因素建立层次性的安全性指标体系，使用层次分析法确定指标权重；然后借助安全工具的测试结果，使用模糊综合评估法构造前向神经网络；最后，使用神经网络的反向传播算法调整指标权重。在此模型的基础上，设计并实现了一个信息息系统安全性评估系统。

A Comprehensive Security Evaluation Model of Information Systems Based on Artificial Neural Networks

This paper proposes a model which combines artificial neural networks and the methods of fuzzy comprehensive evaluation.It first creates a hierarchical criterion model according to the components of information systems and the security elements,computes the weight of each criterion by the AHP method.Then with the help of various security tools,it constructs a forward artificial neural network by fuzzy comprehensive evaluation methods.Finally,it tunes the weights with the BP algorithm.Based on this model,a security evaluation software of information systems is implemented.