Research on the Application of Neural Networks to the Security and Risk Assessment of Information

It has limitations to apply the traditional mathematical model to assess the risk of the information security for it is characterized by its nonlinearity and uncertainty. The RBF Neural Networks Theory, Particle Swarm Optimization (PSO) Analysis and Fuzzy Evaluation are combined to build a particle swarm optimizing model of Information Security Risk Assessment based on RBF Neural Networks, so as to improve the performance of the security and risk assessment. First, quantify the factors of the risk of information security by fuzzy system to input the fuzzy system output to the model of the RBF Neural Networks. Then apply Particle Swarm Optimization (PSO) to optimize and train the parameters of the RBF Neural Networks. Finally, the optimizing assessment model is built. The results of simulation experiments in progress indicate that the improved RBF Neural Network model eliminates the defects of the traditional assessment, such as high subjectivity and fuzzy result and so on to enable the risk assessment of information system. Moreover, the RBF Neural Networks boast higher fitting precision, better learning capability and higher rate of convergence.