Adversarial perturbation of images, in which a source image is deliberately modified with the intent of causing a classifier to misclassify the image, provides important insight into the robustness of image classifiers. In this work we develop two new methods for constructing adversarial perturbations, both of which are motivated by minimizing human ability to detect changes between the perturbed and source image. The first of these, the Edge-Aware method, reduces the magnitude of perturbations permitted in smooth regions of an image where changes are more easily detected. Our second method, the Color-Aware method, performs the perturbation in a color space which accurately captures human ability to distinguish differences in colors, thus reducing the perceived change. The Color-Aware and Edge-Aware methods can also be implemented simultaneously, resulting in image perturbations which account for both human color perception and sensitivity to changes in homogeneous regions. Because Edge-Aware and Color-Aware modifications exist for many image perturbations techniques, we also focus on computation to demonstrate their potential for use within more complex perturbation schemes. We empirically demonstrate that the Color-Aware and Edge-Aware perturbations we consider effectively cause misclassification, are less distinguishable to human perception, and are as easy to compute as the most efficient image perturbation techniques. Code and demo available at https://github.com/rbassett3/Color-and-Edge-Aware-Perturbations
翻译:图像的Adversarial 扰动, 其中刻意修改图像源的图象, 目的是让图像分类者对图像进行错误分类, 从而对图像分类者的稳健性提供重要的洞察力。 在这项工作中, 我们开发了两种构建对抗性扰动的新方法, 这两种方法的动机都是最大限度地降低人类在扰动图像和源图像之间检测变化的能力。 其中第一个方法, 即 Edge- Aware 方法, 减少了在图像平滑、 更便于检测变化的区域允许的扰动程度。 我们的第二个方法, 颜色- Aware 方法, 在一个颜色空间里进行扰动, 准确地捕捉人类区分颜色差异的能力, 从而减少人们所察觉的变化。 彩色- Aware 和 Edge- Aware- Aware 方法, 既考虑到人类的色彩感知力,又考虑到对同类区域变化的敏感度。 因为Edge- Aware- Award- Askreforation 技术, 我们还侧重于在更复杂的扰动性/ abrubligistrual- Procial- viciation 上, 以及我们无法理解。