The Role of Machine Learning in Enhancing ADS-B Communication Security: A Comprehensive Review
Waqas Ahmed · Premier Journal of Computer Science · 2025
ADS-B in air traffic management (ATM) is among the significant technologies developed to improve airspace proficiency. However, it is linked with some vulnerabilities, such as jamming, spoofing, and data injection attacks, which pose a significant risk to aviation safety. The aim of the current study is to focus on security issues and potential solutions through machine learning (ML) to increase the communication security of ADS-B. The main ML types are supervised, unsupervised, and deep learning models that assist in identifying abnormal behavior of in-flight data, predicting evolving threats, and detecting spoofing attempts. ML techniques assess the historical data and indicate potential system failure and vulnerabilities. A proactive response is possible through real-time deep learning methods to ensure the operational efficiency of the ATM following ADS-B. ML models have scalability issues and computational complexities that indicate the use of mixed methods to increase the identification of security issues, as there can be a larger dataset, and every ML technique cannot process such a larger dataset for real-time threat mitigation. ADS-B security is increased due to collaborative efforts and innovations that can resolve the complicated evolving risks in ATM.