Cooperative localization method of UAV formation under deception jamming based on GAN-TM

In this paper, a combination of GAN (generative adversarial network) and trust model is proposed to prevent deception jamming of UAV formation. The method uses GAN to detect the anomalies of the overall position state of the formation, and then establishes a trust model (TM) between each aircraft, via comparing the integrated trust value of each aircraft, the specific number of the deceived UAVs have been detected. The simulation results show that the proposed method has high accuracy and stability in detecting deceived UAVs. At the same time, the method does not need to gather abnormal samples for net training, nor does it need new data interactions when judging the deceived UAVs.