arrow
返回

ELAA: An efficient local adversarial attack using model interpreters

delete2021-09-19
delete5
delete
OA
AI
S
Shangwei Guo
S
Siyuan Geng
向
向涛 (Tao Xiang) *
H
Hangcheng Liu
R
Ruitao Hou
DOI:10.1002/int.22680delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Modern deep neural networks are highly vulnerable to adversarial examples, which attracts more and more researchers' attention to craft powerful adversarial examples. Most of these generation algorithms create global perturbations that would affect the visual quality of adversarial examples. To mitigate such drawbacks, some attacks attempt to generate local perturbations. However, existing local adversarial attacks are time-consuming and the generated adversarial examples are still distinguishable from clean images. In this paper, we propose a novel efficient local adversarial attack (ELAA) using model interpreters to generate severe local perturbations and improve the imperceptibly of the generated adversarial examples. Specifically, we take advantage of model interpretation methods to search the discriminative regions of clean images. Then, we generate local adversarial examples by adding masks to original clean images. We also propose a new optimization method to reduce the redundancy of local perturbations. Through extensive experiments, we show our ELAA can maintain a high attack ability while preserving the visual quality of clean images. Experimental results also demonstrate our local attack outperforms state-of-the-art local attack methods under various system settings.
Keyword:
adversarial example
local attack
machine learning interpreter
saliency map

期刊

International Journal of Intelligent Systems 封面图
International Journal of Intelligent Systems
IF:
3.7
论文数:
3.1K
被引数:
8.1K

机构

C
Chongqing University
学者数:
5.1W
论文数: 4.1W
被引数: 6.0W
G
Guangzhou University
学者数:
1.8W
论文数: 1.3W
被引数: 1.8W
引用论文

引用论文

A New Route for the Total Synthesis of 6,7‐Dihydroeponemycin
err2003-11-19
err0
PREAI
errBibia Bennacer; Christian Rivalle; David S. Grierson
err分享
err收藏
Mask-guided noise restriction adversarial attacks for image classification
err2021-01-01
err13
PREAI
errDuan, Yexin; Zhou, Xingyu; Zou, Junhua; Qiu, Junyang; Zhang, Jin; Pan, Zhisong
err分享
err收藏
Assessing a New Coupled Data Assimilation System Based on the Met Office Coupled Atmosphere–Land–Ocean–Sea Ice Model
err2015-10-29
err0
errOAAI
errD. J. Lea; I. Mirouze; M. J. Martin; R. R. King; A. Hines; D. Walters; M. Thurlow
err分享
err收藏
err分享
err收藏
FineFool: A novel DNN object contour attack on image recognition based on the attention perturbation adversarial technique
err2021-05-01
err24
PREAI
errChen, Jinyin; Zheng, Haibin; Xiong, Hui; Chen, Ruoxi; Du, Tianyu; Hong, Zhen; Ji, Shouling
err分享
err收藏
学者 查看更多内容