Block-wise Image Transformation with Secret Key for Adversarially Robust Defense
share
In this paper, we propose a novel defensive transformation that enables us to maintain a high classification accuracy under the use of both clean images and adversarial examples for adversarially robust defense. The proposed transformation is a block-wise preprocessing technique with a secret key to input images. We developed three algorithms to realize the proposed transformation: Pixel Shuffling, Bit Flipping, and FFX Encryption. Experiments were carried out on the CIFAR-10 and ImageNet datasets by using both black-box and white-box attacks with various metrics including adaptive ones. The results show that the proposed defense achieves high accuracy close to that of using clean images even under adaptive attacks for the first time. In the best-case scenario, a model trained by using images transformed by FFX Encryption (block size of 4) yielded an accuracy of 92.30 attack with a noise distance of 8/255, which is close to the non-robust accuracy (95.45 72.18 the standard accuracy (73.70 proposed algorithms are demonstrated to outperform state-of-the-art defenses including adversarial training whether or not a model is under attack.
READ FULL TEXT