As a malicious attack targeting on the GPS receiver, GPS spoofing attack interferes the normal received satellite signal by reproducing or relaying the signal, resulting in severe position deviation. Such attack has posed significant security threat to unmanned-aerial-vehicles (UAVs), especially in the era of low-altitude economics. However, due to the similarity of the spoofing and intended signal, and the presence of noise, accurate detection and recognition of GPS spoofing attack still remains a challenging issue, particularly in the case of limited samples. In this article, we apply the AdaBoost-CNN algorithm, which combines multiple weak convolutional neural network (CNN) classifiers into a strong classification model, to achieve GPS spoofing attack recognition. To further improve the recognition accuracy when there are very limited samples, we improve the AdaBoost-CNN algorithm by transferring previous network parameters to subsequent CNN. Both simulated and real measurement data are employed to verify the effectiveness of the proposed scheme. It is shown that the recognition accuracy can reach up to 93.75% and 95.83% with 160 simulated samples and 120 measured samples, respectively.

Accurate unmanned aerial vehicles (UAVs) identity recognition with electromagnetic signal is a paramount but challenging issue for low-altitude aerial security, due to the existence of interference and noise. Considering the inherent frequency-hopping (FH) characteristics of UAV command and control signal, we propose a FH signal recognition scheme with template matching, which consists of two steps: (i) Template making, where the FH signals in one cycle are recorded as a binarized spectrogram. This spectrogram encapsulates essential information such as dwell time, bandwidth, and FH mode. The uniqueness of these templates ensures robust recognition in scenarios involving multiple UAVs. (ii) Template matching, where the template slides across the spectrograms and performs dot product. We design and compute similarity metrics to quantify the similarity between the templates and the FH signals within spectrograms, thus obtaining recognition results. Our proposed method achieves an average recognition accuracy of above 99.1% for single UAV scenarios and 97.7% for multiple UAV scenarios, based on an open-source dataset.