Abstract
The article is devoted to the study of the use of machine learning for the analysis of cyber attacks. The study examines Random Forest, SVM and Logistic Regression algorithms, which successfully cope with the tasks of detecting anomalies and minimizing false positives. Adapting models to work with unbalanced data, such as using LabelEncoder for categorical features and StandardScaler for data standardization, has significantly improved their performance. Based on the analysis of data from the «Real-Time Internet of Things (RT-IoT 2022)» set, the results of the accuracy and stability of the models are presented. The main focus is on protecting against cyber threats, including information leaks, DDoS attacks, and other types of threats. An analysis of various machine learning algorithms for cyberattack research has shown significant results. Random Forest has demonstrated the highest accuracy – 99,86%, providing high stability and efficiency in classifying various types of threats. SVM showed an accuracy of 99,29%, coping with most complex classes. Logistic Regression showed satisfactory results with an accuracy of 97,71%, although in some rare cases the accuracy was lower. Thus, Random Forest and SVM have demonstrated the best performance for security and cyberattack analysis tasks in digital systems, providing high accuracy and reliability. In the future, it is planned to introduce more sophisticated methods, such as deep learning, to more accurately identify and analyze threats.