返回
Adaptive iterative attack towards explainable adversarial robustness
DOI:10.1016/j.patcog.2020.107309.png)
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
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
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Active multi-kernel domain adaptation for hyperspectral image classification
PATTERN RECOGNITION
IF7.6
X-ray investigation of the coordination and complex formation of lanthanoid ions in aqueous perchlorate and selenate solutions高氯酸盐和硒酸水溶液中镧系离子的配位和络合物形成的x射线研究
A targeting sequence directs DNA methyltransferase to sites of DNA replication in mammalian nuclei
Cell
IF0
Assessment of neurological manifestations in hospitalized patients with COVID‐19Covid-19住院患者神经系统表现的评估
Weakly Supervised Deep Metric Learning for Community-Contributed Image Retrieval用于社区贡献图像检索的弱监督深度度量学习

