Autonomous detection of malicious events using machine learning models in drone networks

Abstract

Drone systems, the so-called Unmanned Autonomous Vehicles (UAVs), have been widely employed in military and civilian sectors. Drone systems have been used for cyber warfare, warfighting and surveillance purposes of modern military and civilian applications. However, they have increasingly suffered from sophisticated malicious activities that exploit their vulnerabilities through network communications. As drones comprise a complex infrastructure as piloted aircraft but without operators, they still need a reliable security control to assert their safe operations. This paper proposes an autonomous intrusion detection scheme for discovering advanced and sophisticated cyberattacks that exploit drone networks. A testbed was configured to launch malicious events against a drone network for collecting legitimate and malicious observations and evaluate the performances of machine learning in real-time. Machine learning algorithms, including decision tree, k-nearest neighbors, naive Bayes, support vector machine and deep learning multi-layer perceptron, were trained and evaluated using the data collections, with promising results in terms of detection accuracy, false alarm rates, and processing times.