Securing ADS-B Communication: A Survey of Cryptographic and Machine Learning Approaches

Automatic Dependent Surveillance-Broadcast (ADS-B) is fundamental to modern aviation, providing real-time aircraft tracking and improving air traffic management. It is susceptible to threats such as spoofing, jamming, and eavesdropping, as well as threatening operational security and passenger privacy. Conversely, its open communication protocol renders it susceptible. We surveyed cryptographic and machine learning techniques to secure legacy ADS and showed their applicability to present and future UAV networks. Data integrity and authenticity are ensured through cryptographic methods, including encryption, lightweight, and hybrid techniques. Real-time threat mitigation can be addressed adaptively using machine learning techniques, such as anomaly detection and attack classification. These approaches are compared, emphasizing their strengths and weaknesses while asserting the necessity and feasibility of hybrid strategies. Future research should focus on scalable quantum-resistant cryptographical techniques, robust machine-learning models, and global standards for ADS-B security.