ADAPTATION OF MULTI-FACTOR FORECASTING ALGORITHM FOR DETECTING NETWORK VULNERABILITIES

Network security understandably remains one of the fastest changing areas in the digital world. In addition, with the development of new technologies and the emergence of new cyber attacks, the obsolescence of security methods and technologies occurs at a rapid pace. Nowadays, network and computer security in production environments is becoming increasingly important due to the growing number of cyber attacks and network vulnerabilities. Due to the increase in the number of remotely connected devices, the increase in the volume of data and the complexity of network technologies. Given the large number of vulnerabilities identified each year, automating their prediction is crucial. The objective of this study is to comprehensively analyze network vulnerabilities and attacks using a multi-factor forecasting algorithm. The multi-factor forecasting algorithm improves the accuracy of attack forecasting by taking into account parameters such as network failure rate, network traffic activity and threat response time. The study included a literature review of articles published in Scopus and Web of Science, data collection from various sources, their normalization and analysis using machine learning methods such as neural networks, logistic regression and random forests. The practical value of the study is that the developed algorithm can be used to create systems for monitoring network vulnerabilities and assessing the effectiveness of operation in real time. This significantly improves the protection of corporate and government networks, reduces damage from cyberattacks and improves overall cybersecurity.