Applying Big Data Processing and Machine Learning Methods for Mobile Internet of Things Security Monitoring

Igor Kotenko^1,2+, Igor Saenko^1,2, and Alexander Branitskiy^1,2

¹Laboratory of Computer Security Problems of St. Petersburg Institute for Informatics and Automation (SPIIRAS), 14-th line, 39, Saint-Petersburg, 199178, Russia

²St. Petersburg National Research University of Information Technologies, Mechanics and Optics, 49, Kronverkskiy prospekt, Saint-Petersburg, Russia

{ivkote, ibsaen, branitskiy}@comsec.spb.ru

Abstract

The paper offers a new approach to Big Data processing for security monitoring of mobile Internet of things elements based on machine learning and its implementation using parallel algorithms. The architecture of security monitoring system is considered. It specifies several machine learning mechanisms intended for solving classification tasks. The classifier operation results are exposed to plurality voting, weight voting and soft voting. The experimental assessment of performance and accuracy of the offered methods is made.

Keywords: Big Data, Machine Learning, Security Monitoring, Mobile Security, Internet of Things, Classifier.

+: Corresponding author: Igor Kotenko
Laboratory of Computer Security Problems of St. Petersburg Institute for Informatics and Automation (SPIIRAS), 14-th line, 39, Saint-Petersburg, 199178, Russia

Journal of Internet Services and Information Security (JISIS), 8(3): 54-63, August 2018
DOI: 10.22667/JISIS.2018.08.31.054 [pdf]