arrow
返回

Adaptive iterative attack towards explainable adversarial robustness

delete2020-09-01
delete45
PRE
AI
Y
Yucheng Shi
Y
Yahong Han *
张全新 封面图
张全新 (Quanxin Zhang)
X
Xiaohui Kuang
DOI:10.1016/j.patcog.2020.107309delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Image classifiers based on deep neural networks show severe vulnerability when facing adversarial examples crafted on purpose. Designing more effective and efficient adversarial attacks is attracting considerable interest due to its potential contribution to interpretability of deep learning and validation of neural networks' robustness. However, current iterative attacks use a fixed step size for each noise-adding step, making further investigation into the effect of variable step size on model robustness ripe for exploration. We prove that if the upper bound of noise added to the original image is fixed, the attack effect can be improved if the step size is positively correlated with the gradient obtained at each step by querying the target model. In this paper, we propose Ada-FGSM (Adaptive FGSM), a new iterative attack that adaptively allocates step size of noises according to gradient information at each step. Improvement of success rate and accuracy decrease measured on ImageNet with multiple models emphasizes the validity of our method. We analyze the process of iterative attack by visualizing their trajectory and gradient contour, and further explain the vulnerability of deep neural networks to variable step size adversarial examples. (C) 2020 Elsevier Ltd. All rights reserved.
Keyword:
Adversarial example
Adversarial attack
Image classification
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

T
tianjin university
学者数:
8.0W
论文数: 5.8W
被引数: 88
B
beijing institute of technology
学者数:
5.5W
论文数: 4.0W
被引数: 63
引用论文

引用论文

Active multi-kernel domain adaptation for hyperspectral image classification
err2018-05-01
err117
errOAAI
errDeng, Cheng; Liu, Xianglong; Li, Chao; Tao, Dacheng
err分享
err收藏
Distributed Adaptive Binary Quantization for Fast Nearest Neighbor Search
err2017-11-01
err64
PREAI
errLiu, Xianglong; Li, Zhujin; Deng, Cheng; Tao, Dacheng
err分享
err收藏
ImageNet Large Scale Visual Recognition ChallengeImageNet大规模视觉识别挑战
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
err分享
err收藏
err分享
err收藏
A targeting sequence directs DNA methyltransferase to sites of DNA replication in mammalian nuclei
errCell
IF0
err1992-11-01
err0
errOAAI
errHeinrich Leonhardt; Andrea W. Page; Heinz-Ulrich Weier; Timothy H. Bestor
err分享
err收藏
Assessment of neurological manifestations in hospitalized patients with COVID‐19Covid-19住院患者神经系统表现的评估
err2020-08-24
err0
errOAAI
errM. Luigetti; R. Iorio; A. R. Bentivoglio; L. Tricoli; V. Riso; J. Marotta; C. Piano; G. Primiano; L. Zileri Del Verme; M. R. Lo Monaco; P. Calabresi
err分享
err收藏
学者 查看更多内容