Evaluation of Anomaly Detection-Based Tools in an Industrial Control Systems Environment

This study evaluates Behavioral Anomaly Detection Tools used in an Industrial Control System environment. The goal is to show the usefulness of Behavioral Anomaly Detection-Based capabilities in an Industrial Control Systems (ICS) environment as they are used in their manufacturing processes. Implementing machine learning behavioral anomaly detection devices can provide a key security component in sustaining business operations, particularly those based in ICS. One of the ways to interrupt operations in an industrial control systems environment is to introduce anomalous data into their manufacturing processes, whether knowingly or accidentally. Although the example solutions will focus on cybersecurity, it may also produce benefits to manufacturers in detecting anomalous environments not related to security such as failing parts. Using an Industrial Control Robotics environment, I will evaluate Anomaly Detection Tools used in critical infrastructure, such as public works systems, critical manufacturing systems, and other industrial control systems. The research produced from the use of the environment will support the efforts of industry and government to develop more secure industrial control systems as well as improve the security of existing infrastructure