基于模糊神经网络方法的信息系统安全风险评价研究

Evaluation of Information System Security Risk Based on Fuzzy Neural Network Method

为提高信息系统安全风险评价的准确性,提出基于模糊神经网络的信息系统安全风险评价模型。该模型利用模糊理论隶属度反映各因子的相对状态,对模糊性具有很高的识别精度。将风险因子模糊隶属度矩阵输入BP神经网络中,增加了它对模糊性的识别能力。通过非线性分析处理的BP神经网络进行学习和测试,得到输出风险评价等级。实例分析结果证明算法的应用性。误差分析结果证明了模型的有效性。检验结果表明,模糊神经网络模型的识别精度高于单一的模糊评价模型和神经网络模型。

In order to improve accuracy of information system security risk evaluation, a risk evaluation model based on fuzzy neural network was built. A calculation example was used to show how the method works, and error analysis was applied to validate the model. The fuzzy assessment model, neural network model and fuzzy neural network model were tested, the results show that the accuracy of the fuzzy neural network model is higher than that of the fuzzy assessment model and neural network model.