Adversarial Attacks on Co-Occurrence Features for GAN Detection

Abstract: Improvements in Generative Adversarial Networks (GANs) have greatly reduced the difficulty of producing new, photo-realistic images with unique semantic meaning. With this rise in ability to generate fake images comes demand to detect them. While numerous methods have been developed for this task, the majority of them remain vulnerable to adversarial attacks. In this paper, develop two novel adversarial attacks on co-occurrence based GAN detectors. These are the first attacks to be presented against such a detector. We show that our method can reduce accuracy from over 98% to less than 4%, with no knowledge of the deep learning model or weights. Furthermore, accuracy can be reduced to 0% with full knowledge of the deep learning model details.