General Sparse Adversarial Attack Method for SAR Images Based on Keypoints

With the continuous development of deep learning in the field of synthetic aperture radar (SAR) image processing, it is found that image recognition is vulnerable to interference and the accuracy is greatly reduced. Therefore, if a general adversarial attack method is designed to generate adversarial examples capable of deceiving different types of convolutional neural network models, it can protect target images from being correctly recognized by adversaries and safeguard image privacy information. However, most of the current adversarial attack methods have too large attack scope and interference intensity, and do not have the ability to universally attack different neural network models, resulting in poor concealment, deception, and transfer deception of adversarial attacks. In this article, we propose a general keypoints sparse attack (KPSA) method for SAR images, which achieves excellent deception and transfer deception while controlling the attack range and jamming strength. It is a general and efficient adversarial attack method. KPSA uses the generator to generate intensity interference images and imposes amplitude constraint, uses the keypoints extraction method to generate position interference images to realize sparse attack, uses the difference value loss function to achieve fast convergence of the training model, and achieves transfer deception performance without depending on the type of discriminator. The deception rate and transfer deception rate experiments were conducted on man portable surveillance and target acquisition radar (MSTAR) and automatic target recognition network-surveillance and target acquisition radar (ATRNet-STAR). By comparing with the advanced methods in the field of adversarial attacks, it was verified that the KPSA method is superior to the current advanced methods, and it was confirmed that the KPSA method has application value in various complex practical scenarios.