This paper analyzes the dynamics of cyberattacks and fraud techniques using machine learning algorithms for Industrial Internet of Things (IIoT) systems. Special attention is paid to information security issues of digital twins within the framework of the Industry 4.0 concept. Various machine learning techniques, such as logistic regression, random forest, and the nearest neighbor method, are considered for classifying attacks in IIoT systems, taking into account the problem of data imbalance inherent in rare attacks. The use of data balancing and cross-validation methods can improve the accuracy of the models and minimize the number of false positives. The results demonstrate that the random forest model outperforms other methods in terms of accuracy, confirming its effectiveness for IIoT security and digital twin protection. Additionally, feature selection and optimization techniques were explored to enhance model performance further. The study also highlights the importance of real-time threat detection, which is crucial for maintaining the integrity and resilience of IIoT environments. Future research is planned to investigate more sophisticated methods, including deep learning, to improve attack detection and classification in the context of Industry 4.0. The integration of federated learning and adaptive AI-driven security measures may also offer promising solutions to emerging cyber threats.

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.