ADS-B Multi-Attack Intrusion Detection Dataset with Real and Simulated Air Traffic Scenarios

This dataset supports research on cybersecurity in Automatic Dependent Surveillance–Broadcast (ADS-B) systems and is designed for intrusion detection and anomaly analysis. It combines real-world ADS-B messages collected from the OpenSky Network with simulated attack scenarios generated using the OpenScope air traffic control simulator. The dataset includes nine distinct attack types, such as spoofing, ghost aircraft injection, trajectory manipulation, transponder code alteration, message delay, and other integrity and availability attacks. These attacks are carefully generated to reflect realistic adversarial behaviors while maintaining physical plausibility within the airspace. Each record contains spatial, kinematic, and flight-related attributes (e.g., latitude, longitude, altitude, speed, heading), along with engineered features used for machine learning-based detection. This dataset is intended for: Intrusion detection system (IDS) development Machine learning and anomaly detection research ADS-B security analysis and benchmarking The dataset was used in the study:Ahmed, W., Masood, A., Manzoor, J., & Akleylek, S. (2025). Automatic dependent surveillance-broadcast (ADS-B) anomalous messages and attack type detection: Deep learning-based architecture. PeerJ Computer Science, 11, e2886.