Abnormal Data Detection of Unmanned Aerial Vehicles Based on Double Shortcuts ZB-ResNet

Unmanned aerial vehicles (UAVs) are unmanned aircrafts operated by radio remote control and programmed control equipment. Due to their small size, low cost, and high flexibility, UAV s are widely used in military and civilian fields. Along with the broad applications of UAVs and the significant advancement of information technologies, they also face cyber threats. Among them, false spoofing is a typical cyber-attack. If this attack hits UAV s, it could result in damage to property and the release of private data or classified documents. In this paper, we propose the Double Shortcuts Zero-Bias Residual Network (Double Shortcuts ZB-ResNet) with small storage capacity and low time complexity for abnormal data detection of UAVs. It is designed by combining double shortcuts residual blocks and Zero-Bias (ZB) fully connected layer to anomaly detections. By comparing with the experimental results of the improved Convolutional Neural Networks with ZB layer, the detection accuracy of the Double Shortcuts ZB-ResNet model is improved by nearly two percentage points.