Adversarial Example Defense via Perturbation Grading Strategy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Shaowei, Lyu, Wanli, Li, Bin, Yin, Zhaoxia, Luo, Bin
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929618729041920
author Zhu, Shaowei
Lyu, Wanli
Li, Bin
Yin, Zhaoxia
Luo, Bin
author_facet Zhu, Shaowei
Lyu, Wanli
Li, Bin
Yin, Zhaoxia
Luo, Bin
contents Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2212_08341
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Adversarial Example Defense via Perturbation Grading Strategy
Zhu, Shaowei
Lyu, Wanli
Li, Bin
Yin, Zhaoxia
Luo, Bin
Computer Vision and Pattern Recognition
Machine Learning
Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.
title Adversarial Example Defense via Perturbation Grading Strategy
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2212.08341