This paper describes the process of concatenation of neural network architectures in face image and voice recognition during training. For training of neural networks the extracted features of face image and acoustic signal are used as input vectors. The results obtained and comparative performance of different methods of user recognition of computer information system based on neural networks are presented.

Keywords: biometric authentication, voice, dataset, face image, computer information system, concatenation, neural network

The problem of developing the architecture of a dynamic information security management system for an enterprise information system, based on the hierarchical organization of the management system, analysis of the state of the computer system in the information space, analysis of the spread of risk flow, as well as multi-agent organization of the processes of collecting, analyzing data and making decisions is considered.

Keywords: information protection, enterprise information system, security policy, information security management, risk analysis, zero trust architecture, multi-agent technologies, neural network forecasting