MODERN METHODS OF ENSURING INFORMATION PROTECTION IN CYBERSECURITY SYSTEMS USING ARTIFICIAL INTELLIGENCE AND BLOCKCHAIN TECHNOLOGY

Abstract

This scientific work is devoted to the development and improvement of information protection methods to counteract unauthorized access to information activity facilities and their telecommunication networks. The conclusions of the study indicate the need to implement innovative solutions to increase the level of security in modern cyberspace.

An improved algorithm for determining and transferring node hosts in the Blockchain system is proposed, which uses floating hosts to increase the adaptability of the network to external attacks. This allows to automatically close ports during scanning, making it difficult for attackers to access the system and increasing the overall level of network protection.

A study of GPT models has shown their high efficiency in detecting cyberattacks on information activity facilities and their telecommunication networks. GPT-4.0 has demonstrated increased efficiency in processing and detecting various types of attacks compared to GPT-3.5, which provides faster response time and improves the overall level of security.

The developed method of collecting event logs from decoys based on Blockchain provides high fault tolerance and reliability of logs, which is critically important for protecting information objects and telecommunication networks. The decentralized nature of Blockchain prevents unauthorized editing of information, creating a reliable system for storing attack data.

The developed model of a dynamic system of active traps based on software decoys using Blockchain technology integrates decentralized and automatically updated attributes of traps. This increases the effectiveness of network protection, reduces the load on the infrastructure and the response time of services during attacks, which increases the channel throughput and data transfer rate.

The developed mathematical description of the calculation of dynamic attributes of software decoys takes into account the capabilities of Blockchain Solana, which made it possible to model and optimize the distribution of network resources. This increased the effectiveness of protection and ensured a quick response of services during external attacks.

The method of using Blockchain-based software decoys obtained in the work increases the resources required by the attacker to carry out an attack, which increases the response time of cybersecurity specialists. The use of dynamic Blockchain-based software decoys demonstrates better performance compared to static and other dynamic analogues, increasing the overall level of computer network security. The proposed cybercrime research system detects known attacks 31% faster and is able to detect unknown attacks thanks to training the Isolation Forest model. The time for analyzing cybercrimes has been significantly reduced thanks to the use of the GPT model, which provides an effective and fast response to threats.