Application of Adversarial Sample Attack in Aerial Photo Identification of Transport Vehicle

Abstract

The adversarial samples can cause the convolutional neural network model to output incorrect results. It is proposed to paste the generated adversarial sample patch on the roof of the transport vehicle to prevent aerial identification of the drone and achieve the attack on the target detection system. By producing aerial transport vehicle datasets, a YOLOv2-based target detection model is trained in the Pytorch deep learning framework, and the adversarial patch is trained by the GAN (Generative Adversarial Networks) called adversarial-yolo that can make the target detection failed. After simulation and comparison, the transport vehicle with a small adversarial patch can successfully and stably attack the target detection model, making it unable to detect the target, and the operation is flexible. The research can provide a certain reference value for the defense and camouflage methods of important ground targets against unmanned aerial intelligent detection devices.