Air Traffic Control System Cyber Security Using Humans and Machine Learning

Abstract

Aviation performance depends on education and training of pilots and air traffic controllers (ATCOs) on technical, procedural, crisis management, decision making, leadership and communication skills. Recent incidents and studies, however, show crew members may be caught unaware and errors in human judgement can still occur in air traffic control (ATC) systems even more so in the presence of cyberattacks. This paper focuses on raising situation awareness and decision making of ATCOs with cyberattacks impacting operations in next-generation ATC systems. Our goal is to investigate crew-based cyber security as a layer in making ATC systems resilient to cyber and cyber-physical attacks. Automatic Dependent Surveillance Broadcast (ADS-B) technology is used as the basis of our preliminary investigation due to its widely known security concerns and central role in ATC systems. We present experimental study considerations for assessing cyber readiness and improving training of ATCOs. We propose a Kalman filter based cyber alarm solution approach for a machine learning based aid for ATCOs towards early cyberattack detection and incident response in ATC systems.