The digitalization of the modern economy has led to the emergence of information technologies in various areas of human activity. In addition to positive effects, this has enhanced the problem of countering cyber threats. The implementation of cyber threats often impacts serious consequences, especially when it comes to critical information infrastructure. Malware is an important part of the modern landscape of cyber threats; the most high-profile cybercrimes of recent years are associated with the use of malware. In this regard, the problem area of countering malware is actively developing, and one of the promising areas of research in this area is the creation of methods for detecting malware based on machine learning. However, the weak point of many well-known studies is the construction of reliable data sets for machine learning models, when the authors do not disclose the features of the formation, preprocessing and labeling of data on malware. This fact compromises the reproducibility a lot of studies. This paper proposes a methodology for collecting data on malware activity based on the MITRE ATT&CK matrix and Sigma rules and designed for Windows OS. The proposed methodology is aimed at improving the quality of datasets containing malware and legitimate processes behavior’s features, as well as at reducing the time of data label by an expert method. A software stand was prepared and experiments were carried out for testing the methodology. The results of experiments confirmed applicability of our methodology.