论文标题
几何启发的TOP-K对抗扰动
Geometry-Inspired Top-k Adversarial Perturbations
论文作者
论文摘要
在过去的几年中，对小图像分类器对小型对抗输入扰动的脆弱性进行了广泛的研究。但是，现有扰动的主要目标主要仅限于将正确预测的top-1类更改为不正确的类别，该类别不打算更改TOP-K预测。在许多数字现实世界中，TOP-K预测更为相关。在这项工作中，我们提出了一种快速准确的方法，用于计算Top-K对抗性示例作为简单的多目标优化。我们通过将其与其他对抗性示例制作技术进行比较来证明其功效和性能。此外，基于这种方法，我们提出了TOP-K通用对抗扰动，图像 - 敏锐的微弱扰动，这些扰动会导致大多数自然图像的TOP-K预测中不存在真实类别。我们在实验上表明，我们的方法优于基线方法，甚至改进了寻找普遍的对抗扰动的现有技术。
The brittleness of deep image classifiers to small adversarial input perturbations has been extensively studied in the last several years. However, the main objective of existing perturbations is primarily limited to change the correctly predicted Top-1 class by an incorrect one, which does not intend to change the Top-k prediction. In many digital real-world scenarios Top-k prediction is more relevant. In this work, we propose a fast and accurate method of computing Top-k adversarial examples as a simple multi-objective optimization. We demonstrate its efficacy and performance by comparing it to other adversarial example crafting techniques. Moreover, based on this method, we propose Top-k Universal Adversarial Perturbations, image-agnostic tiny perturbations that cause the true class to be absent among the Top-k prediction for the majority of natural images. We experimentally show that our approach outperforms baseline methods and even improves existing techniques of finding Universal Adversarial Perturbations.
