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).

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。

EdgeFool: 对抗性图像增强滤波器