Industrial Automatic Control Systems and Controllers Annotation << Back Malware Botnet Detection System Based on Data Mining and Machine Learning A.G. Mustafayev The paper proposes a system for detecting autonomous distributed malware that synchronized with an attacker’s commands transmitted over public networks – botnet. Typical botnet architectures and methods for its identification described. Based on the publicly available CTU-13 database, a sample made for training and testing an artificial neural network. A neural network been designed to classify network traffic and to identify botnet-specific abnormal behavior. Keywords: neural networks; malware; data networks; machine learning; botnet. Contacts: E-mail: arslan_mustafaev@mail.ru Pp. 20-26.