Adversarial examples are intentionally perturbed images that mislead
classifiers. These images can, however, be easily detected using denoising
algorithms, when high-frequency spatial perturbations are used, or can be
noticed by humans, when perturbations are large. In this paper, we propose
EdgeFool, an adversarial image enhancement filter that learns structure-aware
adversarial perturbations. EdgeFool generates adversarial images with
perturbations that enhance image details via training a fully convolutional
neural network end-to-end with a multi-task loss function. This loss function
accounts for both image detail enhancement and class misleading objectives. We
evaluate EdgeFool on three classifiers (ResNet-50, ResNet-18 and AlexNet) using
two datasets (ImageNet and Private-Places365) and compare it with six
adversarial methods (DeepFool, SparseFool, Carlini-Wagner, SemanticAdv,
Non-targeted and Private Fast Gradient Sign Methods). Code is available at
this https URL

本文提出了 EdgeFool 这种对抗图像增强滤波器，通过训练具有多任务损失函数的完全卷积神经网络生成增强图像细节变换的修改来实现误分类。在 ImageNet 和 Private-Places365 上使用三个分类器（ResNet-50，ResNet-18 和 AlexNet）评估 EdgeFool，并将其与六种对抗方法（DeepFool，SparseFool，Carlini-Wagner，SemanticAdv，Non-targeted 和 Private Fast Gradient Sign Methods）进行比较。