The article proposes a set of anthropomorphic models for assessing the risks of infrastructural destructivism effects. These models are based on one of the approaches to assessing the risks of infrastructural genesis, which consists in assessing the effect of infra-structural destructivism, consisting in the uncontrolled self-destruction of the information infrastructure. In contrast to existing approaches to assessing the indicators of infrastructural destructivism, the article proposes the use of models that take into ac-count multiple inter-object behavioral interactions of processes based on the anthropomorphic approach. The anthropomorphic approach involves the implementation of algorithms for assessing inter-object interactions according to the principles of development of wildlife. The phenomenon of infrastructural destructivism has a practical explanation associated with the fact that under certain conditions, the simultaneous implementation of destructive impacts on infrastructure objects from various sources can lead to both catastrophic changes (that is, to the complete self-destruction of the information infrastructure) and to minimizing the risks of infrastructural genesis. The article introduces the concept of the "health" metric in the infrastructure information security monitoring system, which displays the presence of "negative" behavioral activities of processes and thereby predicts an increase in the probability of the appearance of infra-structure destructiveness effects. Thus, when applying the proposed models, it becomes possible to increase the accuracy of assessing the risks of infrastructure genesis, and therefore ensure a sufficient level of information security.

Keywords: infrastructure destructiveness, destructive impacts of infrastructure genesis, anthropo-morphic approach, intelligent analysis of event logs, behavioral analysis

This article discusses the use of universal adversarial as well as to improve the effectiveness of protection systems against robots and spam. In particular, the key features that need to be taken into account to ensure an optimal level of protection against robots and spam are considered. It is also discussed why modern methods of protection are ineffective, and how the use of universal adversarial attacks can help eliminate existing shortcomings. The purpose of this article is to propose new approaches and methods of protection that can improve the effectiveness and stability of protection systems against robots and spam.

Keywords: machine learning, clustering, data recognition, library Nanonets, library Tesseract