Cevik, NursahAkleylek, Sedat2024-05-192024-05-1920242169-3536https://doi.org10.1109/ACCESS.2024.3369181https://hdl.handle.net/20.500.12713/5007This paper focuses on the vulnerabilities of ADS-B, one of the avionics systems, and the countermeasures taken against these vulnerabilities proposed in the literature. Among the proposed countermeasures against the vulnerabilities of ADS-B, anomaly detection methods based on machine learning and deep learning algorithms were analyzed in detail. The advantages and disadvantages of using an anomaly detection system on ADS-B data are investigated. Thanks to advances in machine learning and deep learning over the last decade, it has become more appropriate to use anomaly detection systems to detect anomalies in ADS-B systems. To the best of our knowledge, this is the first survey to focus on studies using machine learning and deep learning algorithms for ADS-B security. In this context, this study addresses research on this topic from different perspectives, draws a road map for future research, and searches for five research questions related to machine learning and deep learning algorithms used in anomaly detection systems.eninfo:eu-repo/semantics/openAccessDeep LearningAircraftAnomaly DetectionSurveysIntrusion DetectionDatabasesComputer SecurityMachine LearningAds-BAnomaly Based Intrusion Detection SystemAnomaly Detection SystemCyber SecurityAvionics SecurityDeep LearningIdsIntrusion Detection SystemMachine LearningArticle123564335662WOS:0011847669000012-s2.0-85186106717N/A10.1109/ACCESS.2024.3369181Q1