Research on Risk Assessment of Information Security Based on Improved Neural Network
Lingxia Liu · Jisuanji fangzhen · 2011
Focused on the uncertainty and complexity of risk assessment of information security and limitation of current methods,we proposed an evaluating method of risk assessment of information security based on particle swarm RBF neural network(PSO-RBF) by means of integrating the artificial neural network and particle swarm optimization algorithm.Firstly,the risk factors were quantized by fuzzy evaluation method,and the input of ANN was fuzzily pre-treated.Secondly,the RBFNN was trained by particle swarm optimization algorithm.Lastly,a model of risk assessment of information security based on PSO-RBF was established.The simulation results show that level of the information security risk factors can be assessed quantitatively by the PSO-RBF neural network model,and the shortcomings of current assessment methods,such as more subjectivity,randomness and fuzzy conclusion.can be overcome.PSO-RBF neural network has higher precision and faster convergence than traditional neural network.