RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression

Jung-Woo Chang, Mojan Javaheripi, Seira Hidano, F. Koushanfar
{"title":"RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression","authors":"Jung-Woo Chang, Mojan Javaheripi, Seira Hidano, F. Koushanfar","doi":"10.14722/ndss.2023.23165","DOIUrl":null,"url":null,"abstract":"Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial attacks on deep learning-based video compression and downstream classification systems. Our attack framework, dubbed RoVISQ, manipulates the Rate-Distortion ($\\textit{R}$-$\\textit{D}$) relationship of a video compression model to achieve one or both of the following goals: (1) increasing the network bandwidth, (2) degrading the video quality for end-users. We further devise new objectives for targeted and untargeted attacks to a downstream video classification service. Finally, we design an input-invariant perturbation that universally disrupts video compression and classification systems in real time. Unlike previously proposed attacks on video classification, our adversarial perturbations are the first to withstand compression. We empirically show the resilience of RoVISQ attacks against various defenses, i.e., adversarial training, video denoising, and JPEG compression. Our extensive experimental results on various video datasets show RoVISQ attacks deteriorate peak signal-to-noise ratio by up to 5.6dB and the bit-rate by up to $\\sim$ 2.4$\\times$ while achieving over 90$\\%$ attack success rate on a downstream classifier. Our user study further demonstrates the effect of RoVISQ attacks on users' QoE.","PeriodicalId":199733,"journal":{"name":"Proceedings 2023 Network and Distributed System Security Symposium","volume":"25 9","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 2023 Network and Distributed System Security Symposium","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14722/ndss.2023.23165","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial attacks on deep learning-based video compression and downstream classification systems. Our attack framework, dubbed RoVISQ, manipulates the Rate-Distortion ($\textit{R}$-$\textit{D}$) relationship of a video compression model to achieve one or both of the following goals: (1) increasing the network bandwidth, (2) degrading the video quality for end-users. We further devise new objectives for targeted and untargeted attacks to a downstream video classification service. Finally, we design an input-invariant perturbation that universally disrupts video compression and classification systems in real time. Unlike previously proposed attacks on video classification, our adversarial perturbations are the first to withstand compression. We empirically show the resilience of RoVISQ attacks against various defenses, i.e., adversarial training, video denoising, and JPEG compression. Our extensive experimental results on various video datasets show RoVISQ attacks deteriorate peak signal-to-noise ratio by up to 5.6dB and the bit-rate by up to $\sim$ 2.4$\times$ while achieving over 90$\%$ attack success rate on a downstream classifier. Our user study further demonstrates the effect of RoVISQ attacks on users' QoE.
RoVISQ:通过基于深度学习的视频压缩对抗性攻击降低视频服务质量
视频压缩通过在给定带宽预算下最大化最终用户体验质量(QoE),在视频流和分类系统中起着至关重要的作用。在本文中,我们对基于深度学习的视频压缩和下游分类系统的对抗性攻击进行了首次系统研究。我们的攻击框架,称为RoVISQ,操纵视频压缩模型的率失真($\textit{R}$ - $\textit{D}$)关系,以实现以下一个或两个目标:(1)增加网络带宽,(2)降低最终用户的视频质量。我们进一步设计了针对下游视频分类服务的目标攻击和非目标攻击的新目标。最后,我们设计了一个实时干扰视频压缩和分类系统的输入不变扰动。与之前提出的视频分类攻击不同,我们的对抗性扰动首先经受住了压缩。我们从经验上展示了RoVISQ攻击对各种防御的弹性,即对抗性训练,视频去噪和JPEG压缩。我们在各种视频数据集上的广泛实验结果表明,RoVISQ攻击使峰值信噪比降低了5.6dB,比特率降低了$\sim$ 2.4 $\times$,同时在下游分类器上实现了超过90 $\%$的攻击成功率。我们的用户研究进一步证明了RoVISQ攻击对用户QoE的影响。
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 求助全文
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