GNSS Spoofing Detection Method Based on BP Neural Network

Spoofing interference have become one of the main threats in Global Navigation Satellite System (GNSS) receiver applications. The efficiency of spoofing detection method based on traditional inertial navigation systems (INS) is affected by INS errors. We propose a GNSS spoofing detection method based on back propagation (BP) neural network to address this problem. Based on the consistency check method assisted by INS velocity information, a spoofing test statistic is constructed, and the BP neural network algorithm is used to predict the test statistic offset caused by INS velocity error. By using the prediction offset to correct the actual measurement data, the impact of INS errors on detection performance is suppressed. The simulation experiments show that the proposed method is suitable for detecting both position spoofing and velocity spoofing, and is sensitive to spoofing interference smaller than the INS velocity error. It is suitable for INS with different accuracies.