文章基本信息

标题：Search Space of Adversarial Perturbations against Image Filters
本地全文：下载
作者：Dang Duy Thang ; Toshihiro Matsui
期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2020
卷号：11
期号：1
页码：11-19
出版社：Science and Information Society (SAI)
摘要：The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker’s intent to deceive the deep learning system. There are many proposed defensive methods to protect deep learning systems against adversarial examples. However, there is still lack of principal strategies to deceive those defensive methods. Any time a par-ticular countermeasure is proposed, a new powerful adversarial attack will be invented to deceive that countermeasure. In this study, we focus on investigating the ability to create adversarial patterns in search space against defensive methods that use image filters. Experimental results conducted on the ImageNet dataset with image classification tasks showed the correlation between the search space of adversarial perturbation and filters. These findings open a new direction for building stronger offensive methods towards deep learning systems.
关键词：Deep neural networks; image filters; adversarial examples; image classification