Nowadays, the Internet has become an integral part of our lives, providing access to a huge amount of information and services. However, along with this, the number of destructive Internet resources that can harm users, especially children and adolescents, is growing. In this regard, there is a need to create an effective system for regulating access to such resources. The article presents an expert system for regulating access to destructive Internet resources, developed on the basis of modern technologies and methods of artificial intelligence. The system allows to automatically detect and block access to resources containing malicious content, as well as provides an opportunity for manual configuration and access control. The article describes the main components of the system and presents images demonstrating the work of the system for blocking access to destructive resources. The article will be useful for specialists in the field of information security, artificial intelligence and protection of children from malicious content on the Internet.

Keywords: destructive content, expert system, information security, Internet resources, SpaCy, Keras, RNN, LSTM, PyQt5, vectorization

Destructive information in text is widespread and dangerous for children and teenagers as well as for adults. Current methods of searching destructive information in text: “keyword search”, “reverse document frequency method” have a number of disadvantages that can cause false positives, which reduces the accuracy of their work. In this article we consider a new developed method of searching destructive information in text, which is used in Python module. This method utilizes Spacy, pymorphy3 libraries which allows us to examine the sentence in detail and delve into its meaning. The developed method reduces false positives and thus increases the efficiency of its use. The paper shows the schemes of sentence parsing, the algorithm of the new method, as well as figures demonstrating its work. The comparative analysis of the new method with analogs is shown.

Keywords: Spacy, disruptive content, information security, TF-IDF, keyword search, pymorphy3, Net Nanny, CyberPatrol, Oculus, child protection

Images on web-sites, social networks, computers may contain destructive content and pose a threat to the psyche of a child or adolescent. Conventional image classification does not always classify it correctly and accordingly has a number of drawbacks due to which there can be false positives, which reduces the accuracy of classification. The paper presents a method in Python module that can detect malicious content in images. The method described in the paper is based on the use of Yolov8 library, which provides good classification of images and further analysis. Using the developed method it was possible to reduce the number of false positives, which led to an increase in its efficiency. The paper shows the scheme of operation of the new method, as well as demonstrated the search for objects in images. Similar programs are considered and their comparative analysis with the developed method is carried out.

Keywords: Spacy, disruptive images, information security, pymorphy3, ultralytics, disruptive text, disruptive content, YoloV8, child safety, benchmarking, digital hash