Generalizing universal adversarial perturbations for deep neural networks

Zhang, Yanghao and Ruan, Wenjie and Wang, Fu and Huang, Xiaowei (2023) Generalizing universal adversarial perturbations for deep neural networks. Machine Learning. ISSN 0885-6125

Full text not available from this repository.

Abstract

Previous studies have shown that universal adversarial attacks can fool deep neural networks over a large set of input images with a single human-invisible perturbation. However, current methods for universal adversarial attacks are based on additive perturbation, which enables misclassification by directly adding the perturbation on the input images. In this paper, for the first time, we show that a universal adversarial attack can also be achieved through spatial transformation (non-additive). More importantly, to unify both additive and non-additive perturbations, we propose a novel unified yet flexible framework for universal adversarial attacks, called GUAP, which can initiate attacks by ℓ∞ -norm (additive) perturbation, spatially-transformed (non-additive) perturbation, or a combination of both. Extensive experiments are conducted on two computer vision scenarios, including image classification and semantic segmentation tasks, which contain CIFAR-10, ImageNet and Cityscapes datasets with a number of different deep neural network models, including GoogLeNet, VGG16/19, ResNet101/152, DenseNet121, and FCN-8s. Empirical experiments demonstrate that GUAP can obtain higher attack success rates on these datasets compared to state-of-the-art universal adversarial attacks. In addition, we also demonstrate how universal adversarial training benefits the robustness of the model against universal attacks. We release our tool GUAP on https://github.com/TrustAI/GUAP.

Item Type:
Journal Article
Journal or Publication Title:
Machine Learning
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1702
Subjects:
?? deep learningadversarial examplessecuritydeep neural networksartificial intelligencesoftware ??
ID Code:
224351
Deposited By:
Deposited On:
25 Sep 2024 15:30
Refereed?:
Yes
Published?:
Published
Last Modified:
25 Sep 2024 15:30