Abnormal Signal Detection Method Based on Bimodal Fusion

Unmanned Aerial Vehicles (UAVs) have been widely used in the fields of military and civilian due to their small size, low cost, and high flexibility. However, various security threats gradually increase by continuously expanding the scopes of UAVs’ applications. Among all the security threats, the false spoofing attack is a typical network threat faced by UAVs. In real scenes, there is inevitably a large amount of random noise in the collected signals of UAVs, which leads to interference of original signals of UAVs, thus affecting the detection accuracy of abnormal signals for UAVs. This paper proposes an abnormal signals detection method for UAVs based on bimodal fusion. First, the collected signals of UAVs are modally transformed to generate waveform images. Second, the Double Shortcuts Zero-Bias ResNet is used to extract bimodal features from the waveform image modal data and the frequency-domain signal modal data of original signals for UAVs. Then, the bimodal fusion classifier is used to fuse the classification results of different modal data to alleviate the interference of random noises to the original signal of UAVs and improve the detection accuracy of abnormal signals on UAVs. Simulation results indicate that based on the original ADS-B signal data set of UAVs with random noises, the proposed method can improve the detection accuracy compared with the existing abnormal signal detection methods.