Generation of Synthetic Data to Improve Security Monitoring for Cyber-Physical Production Systems

Abstract

Machine learning based security monitoring can be used to detect cyberattacks and malfunctions in cyber-physical production systems. Acquiring real data sets for training machine learning algorithms is a problem due to high costs, low data quality, data diversity, and the violation of privacy policies. This paper introduces CyberSyn, a novel approach to generate synthetic data sets for machine learning based security monitoring systems. The generated data sets are analyzed using data quality metrics. Two scenarios from process manufacturing and industrial communication networks are used to evaluate the introduced approach. The proposed approach is able to generate synthetic data sets for both scenarios.