Comparison of machine learning based anomaly detection methods for ADS-B system

This paper introduces an anomaly/intrusion detection system utilizing machine learning techniques for detecting attacks in the Automatic Detection System-Broadcast (ADS-B). Real ADS-B messages between Türkiye's coordinates are collected to train and test machine learning models. After data collection and pre-processing steps, the authors generate the attack datasets by using real ADS-B data to simulate two attack scenarios, which are constant velocity in-crease/decrease and gradually velocity increase or decrease attacks. The efficacy of five machine learning algorithms, including decision trees, extra trees, gaussian naive bayes, k-nearest neighbors, and logistic regression, is evaluated across different attack types. This paper demonstrates that tree-based algorithms consistently exhibit superior performance across a spectrum of attack scenarios. Moreover, the research underscores the significance of anomaly or intrusion detection mechanisms for ADS-B systems, highlights the practical viability of employing tree-based algorithms in air traffic management, and suggests avenues for enhancing safety protocols and mitigating potential risks in the airspace domain.