Adaptive Temporal Grouping for Black-box Adversarial Attacks on Videos

Zhipeng Wei, Jingjing Chen, Hao Zhang, Linxi Jiang, Yu-Gang Jiang
{"title":"Adaptive Temporal Grouping for Black-box Adversarial Attacks on Videos","authors":"Zhipeng Wei, Jingjing Chen, Hao Zhang, Linxi Jiang, Yu-Gang Jiang","doi":"10.1145/3512527.3531411","DOIUrl":null,"url":null,"abstract":"Deep-learning based video models, which have remarkable performance on action recognition tasks, are recently proved to be vulnerable to adversarial samples, even those generated in the black-box setting. However, these black-box attack methods are insufficient to attack videos models in real-world applications due to the requirement of lots of queries. To this end, we propose to boost the efficiency of black-box attacks on video recognition models. Although videos carry rich temporal information, they include redundant spatial information from adjacent frames. This motivates us to introduce the adaptive temporal grouping (ATG) method, which groups video frames by the similarity of their features extracted from the ImageNet-pretrained image model. By selecting one key-frame from each group, ATG helps any black-box attack methods to optimize the adversarial perturbations over key-frames instead of all frames, where the estimated gradient of key-frame is shared with other frames in each group. To balance the efficiency and precision of estimated gradients, ATG adaptively adjusts the group number by the magnitude of the current perturbation and the current query number. Through extensive experiments on the HMDB-51 dataset and the UCF-101 dataset, we demonstrate that ATG can significantly reduce the number of queries by more than 10% for the targeted attack.","PeriodicalId":179895,"journal":{"name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2022 International Conference on Multimedia Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3512527.3531411","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Deep-learning based video models, which have remarkable performance on action recognition tasks, are recently proved to be vulnerable to adversarial samples, even those generated in the black-box setting. However, these black-box attack methods are insufficient to attack videos models in real-world applications due to the requirement of lots of queries. To this end, we propose to boost the efficiency of black-box attacks on video recognition models. Although videos carry rich temporal information, they include redundant spatial information from adjacent frames. This motivates us to introduce the adaptive temporal grouping (ATG) method, which groups video frames by the similarity of their features extracted from the ImageNet-pretrained image model. By selecting one key-frame from each group, ATG helps any black-box attack methods to optimize the adversarial perturbations over key-frames instead of all frames, where the estimated gradient of key-frame is shared with other frames in each group. To balance the efficiency and precision of estimated gradients, ATG adaptively adjusts the group number by the magnitude of the current perturbation and the current query number. Through extensive experiments on the HMDB-51 dataset and the UCF-101 dataset, we demonstrate that ATG can significantly reduce the number of queries by more than 10% for the targeted attack.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
视频黑盒对抗攻击的自适应时间分组
基于深度学习的视频模型在动作识别任务上表现出色,但最近被证明容易受到对抗性样本的攻击,即使是在黑箱设置中生成的样本。然而,这些黑盒攻击方法由于需要大量的查询,不足以在实际应用中攻击视频模型。为此,我们提出提高黑盒攻击对视频识别模型的效率。视频虽然携带了丰富的时间信息,但也包含了来自相邻帧的冗余空间信息。这促使我们引入自适应时间分组(ATG)方法,该方法通过从imagenet预训练图像模型中提取的视频帧的特征相似性对其进行分组。通过从每组中选择一个关键帧,ATG可以帮助任何黑盒攻击方法优化关键帧上的对抗性扰动,而不是所有帧,其中关键帧的估计梯度与每组中的其他帧共享。为了平衡估计梯度的效率和精度,ATG根据当前扰动的大小和当前查询的数量自适应调整群数。通过对HMDB-51数据集和UCF-101数据集的大量实验,我们证明了ATG可以显著减少目标攻击的查询次数,减少幅度超过10%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Self-Lifting: A Novel Framework for Unsupervised Voice-Face Association Learning DMPCANet: A Low Dimensional Aggregation Network for Visual Place Recognition Revisiting Performance Measures for Cross-Modal Hashing MFGAN: A Lightweight Fast Multi-task Multi-scale Feature-fusion Model based on GAN Weakly Supervised Fine-grained Recognition based on Combined Learning for Small Data and Coarse Label
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1