从特征统计角度提高黑盒目标可移植性

Anqi Zhao
{"title":"从特征统计角度提高黑盒目标可移植性","authors":"Anqi Zhao","doi":"10.1109/ICCECE58074.2023.10135228","DOIUrl":null,"url":null,"abstract":"Adversarial examples are images that can be easily misclassified by deep learning models when small, imperceptible changes are added to them. They pose a security concern for the use of DNNs in practical applications because of their transferability. One mainstream method for black-box targeted attacks is feature space attacks. They mainly focus on iterative attacks and have generally attempted to modify the intermediate feature of source category similar to the feature of target category. In this paper, we explore that certain characteristics of features, such as feature style statistics, might be able to better represent the features themselves, and potentially lead to better transferability compared to simply aligning the source and the target features directly. Based on this, we propose a method which use the relationship between the style statistics of intermediate features and its corresponding category to boost black-box targeted transferability in generative attacks. We demonstrate the effectiveness of this method through experimental results.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Boosting black-box targeted transferability from feature statistic perspective\",\"authors\":\"Anqi Zhao\",\"doi\":\"10.1109/ICCECE58074.2023.10135228\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Adversarial examples are images that can be easily misclassified by deep learning models when small, imperceptible changes are added to them. They pose a security concern for the use of DNNs in practical applications because of their transferability. One mainstream method for black-box targeted attacks is feature space attacks. They mainly focus on iterative attacks and have generally attempted to modify the intermediate feature of source category similar to the feature of target category. In this paper, we explore that certain characteristics of features, such as feature style statistics, might be able to better represent the features themselves, and potentially lead to better transferability compared to simply aligning the source and the target features directly. Based on this, we propose a method which use the relationship between the style statistics of intermediate features and its corresponding category to boost black-box targeted transferability in generative attacks. We demonstrate the effectiveness of this method through experimental results.\",\"PeriodicalId\":120030,\"journal\":{\"name\":\"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCECE58074.2023.10135228\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCECE58074.2023.10135228","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

对抗性示例是一种图像,当添加微小的、难以察觉的变化时,深度学习模型很容易对其进行错误分类。由于深度神经网络的可转移性,它们对在实际应用中使用深度神经网络构成了安全问题。针对黑盒攻击的一种主流方法是特征空间攻击。它们主要关注迭代攻击,一般试图修改源类别的中间特征,类似于目标类别的特征。在本文中,我们探讨了特征的某些特征,如特征样式统计,可能能够更好地表示特征本身,并且与直接对齐源特征和目标特征相比,可能会带来更好的可转移性。在此基础上,提出了一种利用中间特征的风格统计量与其对应类别之间的关系来提高生成攻击中黑盒目标可转移性的方法。通过实验结果验证了该方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Boosting black-box targeted transferability from feature statistic perspective
Adversarial examples are images that can be easily misclassified by deep learning models when small, imperceptible changes are added to them. They pose a security concern for the use of DNNs in practical applications because of their transferability. One mainstream method for black-box targeted attacks is feature space attacks. They mainly focus on iterative attacks and have generally attempted to modify the intermediate feature of source category similar to the feature of target category. In this paper, we explore that certain characteristics of features, such as feature style statistics, might be able to better represent the features themselves, and potentially lead to better transferability compared to simply aligning the source and the target features directly. Based on this, we propose a method which use the relationship between the style statistics of intermediate features and its corresponding category to boost black-box targeted transferability in generative attacks. We demonstrate the effectiveness of this method through experimental results.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信