NDSS 2025 – Duumviri: Detecting Trackers And Mixed Trackers With A Breakage Detector
嗯,用户让我帮忙总结一篇文章的内容,控制在100个字以内,而且不需要用“文章内容总结”之类的开头。我先看看用户提供的文章内容。 这篇文章是关于网络追踪检测的工具Duumviri。作者们提到现有的工具在检测追踪器时可能会误判或者导致功能损坏,所以他们提出了一个机器学习的解决方案。Duumviri可以自动识别非混合追踪器和混合追踪器,并且在测试中表现不错,准确率挺高的。 我需要把重点放在Duumviri的作用、它如何解决现有问题以及它的效果上。控制在100字以内,所以得简洁明了。可能的结构是:介绍工具、解决的问题、方法、效果。 比如:“Duumviri是一种用于检测网络追踪器的工具,通过机器学习自动识别非混合和混合追踪器,减少误判和功能损坏。它利用差异特征,在部分请求级别进行分析,准确率达到97.44%和74.19%,发现了22个未报告的追踪器和26个混合追踪器。” 这样应该符合要求。 </think> Duumviri是一种用于检测网络追踪器的工具,通过机器学习自动识别非混合和混合追踪器,减少误判和功能损坏。它利用差异特征,在部分请求级别进行分析,准确率达到97.44%和74.19%,发现了22个未报告的追踪器和26个混合追踪器。 2025-11-6 20:0:0 Author: securityboulevard.com(查看原文) 阅读量:32 收藏

SESSION
Session 2B: Web Security

Cruise Con 2025

Authors, Creators & Presenters: He Shuang (University of Toronto), Lianying Zhao (Carleton University and University of Toronto), David Lie (University of Toronto)

PAPER
Duumviri: Detecting Trackers and Mixed Trackers with a Breakage Detector
https://www.ndss-symposium.org/wp-con…
Web tracking harms user privacy. As a result, the use of tracker detection and blocking tools is a common practice among Internet users. However, no suchtool can be perfect, and thus there is a trade-off between avoiding breakage (caused by unintentionally blocking some required functionality) and neglecting toblock some trackers. State-of-the-art tools usually rely on user reports and developer effort to detect breakages, which can be broadly categorized into two causes: 1) misidentifying non-trackers as trackers, and 2) blocking mixed trackers which blend tracking with functional components.
We propose Incorporating a machine learning-based break- age detector into the tracker detection pipeline to automatically avoid misidentification of
functional resources. For both tracker detection and breakage detection, we propose using differential features that can more clearly elucidate the differences caused by blocking a request. We designed and implemented a prototype of our proposed approach, Duumviri, for non-mixed trackers. We then adopt it to automatically identify mixed trackers, drawing differential features at partial-request granularity.
In the case of non-mixed trackers, evaluating Duumviri on 15K pages shows its ability to replicate the labels of human-generated filter lists, EasyPrivacy, with an accuracy of 97.44%. Through a manual analysis, we find that Duumviri can identify previously unreported trackers and its breakage detector can identify overly strict EasyPrivacy rules that cause breakage. In the case of mixed trackers, Duumviri is the first automated mixed tracker detector, and achieves a lower bound accuracy of 74.19%. Duumviri has enabled us to detect and confirm 22 previously unreported unique trackers and 26 unique mixed trackers.

Our thanks to the Network and Distributed System Security (NDSS) Symposium for publishing their Creators, Authors and Presenter’s superb NDSS Symposium 2025 Conference content on the organization’s’ YouTube channel.

Permalink

*** This is a Security Bloggers Network syndicated blog from Infosecurity.US authored by Marc Handelman. Read the original post at: https://www.youtube-nocookie.com/embed/pJnVztzU7kQ?si=k43PceGqhswDodIZ


文章来源: https://securityboulevard.com/2025/11/ndss-2025-duumviri-detecting-trackers-and-mixed-trackers-with-a-breakage-detector/
如有侵权请联系:admin#unsafe.sh