Robust long-tailed recognition with distribution-aware adversarial example generation.

IF 6 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Bo Li, Yongqiang Yao, Jingru Tan, Dandan Zhu, Ruihao Gong, Ye Luo, Jianwei Lu
{"title":"Robust long-tailed recognition with distribution-aware adversarial example generation.","authors":"Bo Li, Yongqiang Yao, Jingru Tan, Dandan Zhu, Ruihao Gong, Ye Luo, Jianwei Lu","doi":"10.1016/j.neunet.2024.106932","DOIUrl":null,"url":null,"abstract":"<p><p>Confronting adversarial attacks and data imbalances, attaining adversarial robustness under long-tailed distribution presents a challenging problem. Adversarial training (AT) is a conventional solution for enhancing adversarial robustness, which generates adversarial examples (AEs) in a generation phase and subsequently trains on these AEs in a training phase. Existing long-tailed adversarial learning methods follow the AT framework and rebalance the AE classification in the training phase. However, few of them realize the impact of the long-tailed distribution on the generation phase. In this paper, we delve into the generation phase and uncover its imbalance across different classes. We evaluate the generation quality for different classes by comparing the differences between their generated AEs and natural examples. Our findings reveal that these differences are less pronounced in tail classes compared to head classes, indicating their inferior generation quality. To solve this problem, we propose the novel Distribution-Aware Adversarial Example Generation (DAG) method, which balances the AE generation for different classes using a Virtual Example Creator (VEC) and a Gradient-Guided Calibrator (GGC). The VEC creates virtual examples to introduce more adversarial perturbations for different classes, while the GGC calibrates the creation process to enhance the focus on tail classes based on their generation quality, effectively addressing the imbalance problem. Extensive experiments on three long-tailed adversarial benchmarks across five attack scenarios demonstrate DAG's effectiveness. On CIFAR-100-LT, DAG outperforms the previous RoBal by 4.0 points under the projected gradient descent (PGD) attack, highlighting its superiority in adversarial scenarios.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"106932"},"PeriodicalIF":6.0000,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Networks","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1016/j.neunet.2024.106932","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Confronting adversarial attacks and data imbalances, attaining adversarial robustness under long-tailed distribution presents a challenging problem. Adversarial training (AT) is a conventional solution for enhancing adversarial robustness, which generates adversarial examples (AEs) in a generation phase and subsequently trains on these AEs in a training phase. Existing long-tailed adversarial learning methods follow the AT framework and rebalance the AE classification in the training phase. However, few of them realize the impact of the long-tailed distribution on the generation phase. In this paper, we delve into the generation phase and uncover its imbalance across different classes. We evaluate the generation quality for different classes by comparing the differences between their generated AEs and natural examples. Our findings reveal that these differences are less pronounced in tail classes compared to head classes, indicating their inferior generation quality. To solve this problem, we propose the novel Distribution-Aware Adversarial Example Generation (DAG) method, which balances the AE generation for different classes using a Virtual Example Creator (VEC) and a Gradient-Guided Calibrator (GGC). The VEC creates virtual examples to introduce more adversarial perturbations for different classes, while the GGC calibrates the creation process to enhance the focus on tail classes based on their generation quality, effectively addressing the imbalance problem. Extensive experiments on three long-tailed adversarial benchmarks across five attack scenarios demonstrate DAG's effectiveness. On CIFAR-100-LT, DAG outperforms the previous RoBal by 4.0 points under the projected gradient descent (PGD) attack, highlighting its superiority in adversarial scenarios.

求助全文
约1分钟内获得全文 求助全文
来源期刊
Neural Networks
Neural Networks 工程技术-计算机:人工智能
CiteScore
13.90
自引率
7.70%
发文量
425
审稿时长
67 days
期刊介绍: Neural Networks is a platform that aims to foster an international community of scholars and practitioners interested in neural networks, deep learning, and other approaches to artificial intelligence and machine learning. Our journal invites submissions covering various aspects of neural networks research, from computational neuroscience and cognitive modeling to mathematical analyses and engineering applications. By providing a forum for interdisciplinary discussions between biology and technology, we aim to encourage the development of biologically-inspired artificial intelligence.
×
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