ADS-B Anomaly Data Detection Using SVDD-based LSTM Encoder-Decoder Algorithm

Due to the high accuracy, favorable data share and large coverage, Automatic Dependent Surveillance - Broadcast (ADS-B) surveillance is regarded as the core technology in the next generation air traffic management. However, the ADS-B data is broadcasted with absence of adequate data integrity and authentication support, which leads to various security challenges on information leakage and tampering in the ADS-B system. Hence, anomaly ADS-B data detection is vital to minimize security threats in ADS-B system application, especially for ADS-B data attack with high concealment. In this paper, a novel anomaly data detection method was designed based on the long short-term memory (LSTM) encoder-decoder architecture and Support Vector Domain Description (SVDD) hyper-sphere classifier. The proposed algorithm provided a solution for the ADS-B data reconstruction and adaptive anomalies detection threshold determination. Experiments conducted on the real ADS-B data to compare the proposed method with previous approaches, and the comparison results from which illustrated that the effectiveness and accuracy of the proposed method.