针对信息安全风险评估的不确定性和复杂性以及传统的数学方法在评估信息安全风险等级中的局限性,将人工神经网络理论、小波分析及模糊评价法有机结合,建立了基于模糊小波神经网络的信息安全风险评估模型.采用模糊评价法对风险因素的指标进行量化,将模糊系统的输出作为神经网络的输入,构造模糊小波神经网络并加以训练.仿真结果表明:模糊小波神经网络模型可实现对信息系统的风险因素级别的量化评估,解决现有评估方法所存在的主观随意性大、结论模糊等缺陷,并且比BP神经网络具有更高的拟合精度,收敛速度更快.
Focused on the uncertainty and complexity of risk assessment of information security and limitation of current methods, the artificial neural network (ANN), wavelet analysis and fuzzy mathematics were integrated. A model of risk assessment of information security based on fuzzy wavelet neural network (FWNN) was established. The index of information security risk factors were quantized by fuzzy evaluation method. The outputs of fuzzy system were taken as the inputs of ANN. The fuzzy wavelet neural network was established and trained. The simulation results show that level of the information security risk factors can be assessed quantitatively by the fuzzy wavelet neural network model, and the shortcomings of current assessment methods can be overcome, such as more subjectivity, randomness and fuzzy conclusion. FWNN has higher precision and faster convergence than BP neural network.