更聪明的攻击:注意力驱动的细粒度网页指纹攻击

IF 5.4 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Yali Yuan, Weiyi Zou, Guang Cheng
{"title":"更聪明的攻击:注意力驱动的细粒度网页指纹攻击","authors":"Yali Yuan,&nbsp;Weiyi Zou,&nbsp;Guang Cheng","doi":"10.1016/j.cose.2025.104643","DOIUrl":null,"url":null,"abstract":"<div><div>Website Fingerprinting (WF) attacks aim to infer which websites a user is visiting by analyzing traffic patterns, thereby compromising user anonymity. Although this technique has been demonstrated to be effective in controlled experimental environments, it remains largely limited to small-scale scenarios, typically restricted to recognizing website homepages. In practical settings, however, users frequently access multiple subpages in rapid succession, often before previous content fully loads. WebPage Fingerprinting (WPF) generalizes the WF framework to large-scale environments by modeling subpages of the same site as distinct classes. These pages often share similar page elements, resulting in lower inter-class variance in traffic features. Furthermore, we consider multi-tab browsing scenarios, in which a single trace encompasses multiple categories of webpages. This leads to overlapping traffic segments, and similar features may appear in different positions within the traffic, thereby increasing the difficulty of classification. To address these challenges, we propose an attention-driven fine-grained WPF attack, named ADWPF. Specifically, during the training phase, we apply targeted augmentation to salient regions of the traffic based on attention maps, including attention cropping and attention masking. ADWPF then extracts low-dimensional features from both the original and augmented traffic and applies self-attention modules to capture the global contextual patterns of the trace. Finally, to handle the multi-tab scenario, we employ the residual attention to generate class-specific representations of webpages occurring at different temporal positions. Extensive experiments demonstrate that the proposed method consistently surpasses state-of-the-art baselines across datasets of different scales. Notably, under a challenging setting involving 1,000 monitored webpages, our model achieved a 50.54% mAP and 63.85% Recall@5.</div></div>","PeriodicalId":51004,"journal":{"name":"Computers & Security","volume":"158 ","pages":"Article 104643"},"PeriodicalIF":5.4000,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Attack smarter: Attention-driven fine-grained webpage fingerprinting attacks\",\"authors\":\"Yali Yuan,&nbsp;Weiyi Zou,&nbsp;Guang Cheng\",\"doi\":\"10.1016/j.cose.2025.104643\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Website Fingerprinting (WF) attacks aim to infer which websites a user is visiting by analyzing traffic patterns, thereby compromising user anonymity. Although this technique has been demonstrated to be effective in controlled experimental environments, it remains largely limited to small-scale scenarios, typically restricted to recognizing website homepages. In practical settings, however, users frequently access multiple subpages in rapid succession, often before previous content fully loads. WebPage Fingerprinting (WPF) generalizes the WF framework to large-scale environments by modeling subpages of the same site as distinct classes. These pages often share similar page elements, resulting in lower inter-class variance in traffic features. Furthermore, we consider multi-tab browsing scenarios, in which a single trace encompasses multiple categories of webpages. This leads to overlapping traffic segments, and similar features may appear in different positions within the traffic, thereby increasing the difficulty of classification. To address these challenges, we propose an attention-driven fine-grained WPF attack, named ADWPF. Specifically, during the training phase, we apply targeted augmentation to salient regions of the traffic based on attention maps, including attention cropping and attention masking. ADWPF then extracts low-dimensional features from both the original and augmented traffic and applies self-attention modules to capture the global contextual patterns of the trace. Finally, to handle the multi-tab scenario, we employ the residual attention to generate class-specific representations of webpages occurring at different temporal positions. Extensive experiments demonstrate that the proposed method consistently surpasses state-of-the-art baselines across datasets of different scales. Notably, under a challenging setting involving 1,000 monitored webpages, our model achieved a 50.54% mAP and 63.85% Recall@5.</div></div>\",\"PeriodicalId\":51004,\"journal\":{\"name\":\"Computers & Security\",\"volume\":\"158 \",\"pages\":\"Article 104643\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2025-08-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers & Security\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0167404825003323\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Security","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167404825003323","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

网站指纹(WF)攻击的目的是通过分析流量模式来推断用户访问的网站,从而损害用户的匿名性。虽然这种技术已被证明在受控的实验环境中是有效的,但它仍然主要局限于小规模的场景,通常仅限于识别网站主页。然而,在实际设置中,用户经常快速连续地访问多个子页面,通常在先前的内容完全加载之前。网页指纹(web Fingerprinting, WPF)通过将同一站点的子页面建模为不同的类,将WF框架推广到大规模环境中。这些页面通常共享相似的页面元素,从而降低了类间流量特征的差异。此外,我们考虑了多选项卡浏览场景,其中单个跟踪包含多个类别的网页。这就导致了流量段的重叠,相似的特征可能出现在流量的不同位置,从而增加了分类的难度。为了应对这些挑战,我们提出了一种注意力驱动的细粒度WPF攻击,命名为ADWPF。具体来说,在训练阶段,我们基于注意图对交通的显著区域进行了有针对性的增强,包括注意裁剪和注意掩蔽。然后,ADWPF从原始流量和增强流量中提取低维特征,并应用自关注模块来捕获跟踪的全局上下文模式。最后,为了处理多选项卡场景,我们使用剩余注意力来生成发生在不同时间位置的网页的特定类表示。大量的实验表明,所提出的方法在不同尺度的数据集上始终优于最先进的基线。值得注意的是,在涉及1,000个监控网页的挑战性设置下,我们的模型实现了50.54%的mAP和63.85%的Recall@5。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Attack smarter: Attention-driven fine-grained webpage fingerprinting attacks
Website Fingerprinting (WF) attacks aim to infer which websites a user is visiting by analyzing traffic patterns, thereby compromising user anonymity. Although this technique has been demonstrated to be effective in controlled experimental environments, it remains largely limited to small-scale scenarios, typically restricted to recognizing website homepages. In practical settings, however, users frequently access multiple subpages in rapid succession, often before previous content fully loads. WebPage Fingerprinting (WPF) generalizes the WF framework to large-scale environments by modeling subpages of the same site as distinct classes. These pages often share similar page elements, resulting in lower inter-class variance in traffic features. Furthermore, we consider multi-tab browsing scenarios, in which a single trace encompasses multiple categories of webpages. This leads to overlapping traffic segments, and similar features may appear in different positions within the traffic, thereby increasing the difficulty of classification. To address these challenges, we propose an attention-driven fine-grained WPF attack, named ADWPF. Specifically, during the training phase, we apply targeted augmentation to salient regions of the traffic based on attention maps, including attention cropping and attention masking. ADWPF then extracts low-dimensional features from both the original and augmented traffic and applies self-attention modules to capture the global contextual patterns of the trace. Finally, to handle the multi-tab scenario, we employ the residual attention to generate class-specific representations of webpages occurring at different temporal positions. Extensive experiments demonstrate that the proposed method consistently surpasses state-of-the-art baselines across datasets of different scales. Notably, under a challenging setting involving 1,000 monitored webpages, our model achieved a 50.54% mAP and 63.85% Recall@5.
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
Computers & Security
Computers & Security 工程技术-计算机:信息系统
CiteScore
12.40
自引率
7.10%
发文量
365
审稿时长
10.7 months
期刊介绍: Computers & Security is the most respected technical journal in the IT security field. With its high-profile editorial board and informative regular features and columns, the journal is essential reading for IT security professionals around the world. Computers & Security provides you with a unique blend of leading edge research and sound practical management advice. It is aimed at the professional involved with computer security, audit, control and data integrity in all sectors - industry, commerce and academia. Recognized worldwide as THE primary source of reference for applied research and technical expertise it is your first step to fully secure systems.
×
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:604180095
Book学术官方微信