Adversarial Turing Patterns from Cellular Automata
This research provides a theoretical link between UAPs and Turing patterns, which is significant for understanding the structure of adversarial attacks and developing more robust deep learning models.
This paper explores the connection between universal adversarial perturbations (UAPs) and Turing patterns, which are generated by cellular automata. The authors propose using Turing patterns as UAPs and demonstrate that they significantly degrade the performance of deep learning models, offering a fast and efficient black-box attack.
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.