元胞自动机中的对抗图灵模式
Adversarial Turing Patterns from Cellular Automata
摘要：
最先进的深度分类器很容易受到普遍对抗性扰动的影响：小幅度的单一扰动会导致大多数输入的错误分类。这种现象可能导致严重的安全问题。尽管在这一领域的广泛研究，有一个缺乏理论上的理解，这些扰动的结构。在图像域中，代表这些扰动的模式与经典图灵模式之间存在一定的视觉相似性，经典图灵模式表现为非线性偏微分方程的解，并且是自然界中许多过程的基本概念。在本文中，我们提供了这两个不同的理论之间的理论桥梁，通过映射一个简化的算法制作通用扰动（非齐次）细胞自动机，后者是已知的生成图灵模式。此外，我们建议使用由元胞自动机生成的图灵模式作为通用扰动，并通过实验证明它们会显着降低深度学习模型的性能。我们发现这种方法是一种快速有效的方法，可以在黑盒场景中创建数据不可知的准不可感知的扰动。源代码可在https://github.com/NurislamT/advTuring上获得。
英文摘要：
State-of-the-art deep classifiers are intriguingly vulnerable to universal adversarial perturbations: single disturbances of small magnitude that lead to misclassification of most in-puts. This phenomena may potentially result in a serious security problem. Despite the extensive research in this area,there is a lack of theoretical understanding of the structure of these perturbations. In image domain, there is a certain visual similarity between patterns, that represent these perturbations, and classical Turing patterns, which appear as a solution of non-linear partial differential equations and are underlying concept of many processes in nature. In this paper,we provide a theoretical bridge between these two different theories, by mapping a simplified algorithm for crafting universal perturbations to (inhomogeneous) cellular automata,the latter is known to generate Turing patterns. Furthermore,we propose to use Turing patterns, generated by cellular automata, as universal perturbations, and experimentally show that they significantly degrade the performance of deep learning models. We found this method to be a fast and efficient way to create a data-agnostic quasi-imperceptible perturbation in the black-box scenario. The source code is available at https://github.com/NurislamT/advTuring.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
