论文标题
语义上的对抗性可学习过滤器
Semantically Adversarial Learnable Filters
论文作者
论文摘要
我们提出了一个对抗性框架，以通过考虑图像内容和标签语义来误导分类器来制作扰动。提出的框架结合了结构损失和多任务目标功能中的语义对抗损失，以训练完全卷积的神经网络。结构损失有助于产生扰动，其类型和大小由目标图像处理过滤器定义。语义对抗性损失考虑（语义）标签的组来制作扰动，以防止在同一组中用标签对过滤后的图像{from}进行分类。我们使用三个不同的目标过滤器来验证我们的框架，即详细信息增强，日志转换和伽马校正过滤器；并评估对三个分类器的对抗过滤图像，即RESNET50，RESNET18和ALEXNET，并在Imagenet上进行了预训练。我们表明，所提出的框架生成了具有很高成功率，鲁棒性和向看不见的分类器的过滤图像。我们还讨论了对抗性扰动的客观和主观评估。
We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework combines a structure loss and a semantic adversarial loss in a multi-task objective function to train a fully convolutional neural network. The structure loss helps generate perturbations whose type and magnitude are defined by a target image processing filter. The semantic adversarial loss considers groups of (semantic) labels to craft perturbations that prevent the filtered image {from} being classified with a label in the same group. We validate our framework with three different target filters, namely detail enhancement, log transformation and gamma correction filters; and evaluate the adversarially filtered images against three classifiers, ResNet50, ResNet18 and AlexNet, pre-trained on ImageNet. We show that the proposed framework generates filtered images with a high success rate, robustness, and transferability to unseen classifiers. We also discuss objective and subjective evaluations of the adversarial perturbations.
