The widespread implementation of neural network tools for biometric authentication based on facial and iris images at critical infrastructure facilities has significantly increased the level of security. However, modern requirements dictate the need to modernize these tools to increase resistance to spoofing attacks, as well as to provide a base for assessing the compliance of the psycho-emotional state of personnel with job responsibilities, which is difficult to ensure using traditional monolithic neural network models. Therefore, this article is devoted to the development of a modular neural network model that provides effective biometric authentication for critical infrastructure personnel based on facial images, taking into account the listed requirements. When developing the model, an approach was used in which the functionality of each module was defined in such a way as to correspond to a task traditionally solved by a separate neural network model. This made it possible to use in each individual module a tested and accessible toolkit that has proven its effectiveness in solving the corresponding problem, which, in turn, compared to traditional approaches, allows for a 30–40% increase in the efficiency of the development and adaptation of authentication tools for the conditions of their application. Innovative features of the developed modular model include the ability to recognize spoofing attacks based on environmental artifacts and the naturalness of emotions, as well as an increase in the accuracy of person recognition due to the use of a U-Net neural network to highlight natural facial contours in occlusions. The experimental results show that the proposed model allows for a 5–10% decrease in person recognition error, recognition of spoofing attacks based on the naturalness of emotions and images of background objects, and recognition of the emotional state of personnel, which increases the efficiency of biometric authentication tools.

This article proposes a scientifically grounded approach to risk assessment for infrastructural and functional systems that underpin the development of digitally transformed regional territories under conditions of high threat dynamics and sociotechnical instability. The core methodology is based on modeling of multifactorial threats through the application of fuzzy set theory and logic–linguistic analysis, enabling consideration of parameter uncertainty, fragmented expert input, and the lack of a unified risk landscape within complex infrastructure environments. A special emphasis is placed on components of technogenic, informational, and mobile infrastructure that ensure regional viability across planning, response, and recovery phases. The results confirm the relevance of the approach for assessing infrastructure resilience risks in regional spatial–functional systems, which demonstrates the potential integration into sustainable development strategies at the level of regional governance, cross-sectoral planning, and cultural reevaluation of the role of analytics as an ethically grounded practice for cultivating trust, transparency, and professional maturity.