Adversarial Examples of SAR Images for Deep Learning based Automatic Target Recognition

With the development of deep neural network techniques, an explosion of neural network structures are designed and gained great success in the field of image-based SAR automatic target recognition. Recent studies have shown that machine learning networks are vulnerable to adversarial attacks, which may cause severe security issue. In this paper, a convolution neural network (CNN) for SAR target classification is designed and then attacked by adversarial examples using fast gradient sign method (FGSM) and basic iteration method (BIM). Experiments shown that although the classification accuracy of the model is quite high for real SAR image dataset, elaborately designed tiny perturbation on the data will magnificently reduce the classification performance.