# Towards Fine-Grained Webpage Fingerprinting at Scale

arXiv: https://arxiv.org/abs/2409.04341 · HTML: https://mlsanity.com/paper/2409.04341/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 64 references that are in the map.
- First posted on arXiv 6 Sep 2024.

## Builds on (most cited first, 19 of 19)

- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Deep Metric Learning with Hierarchical Triplet Loss](https://mlsanity.com/paper/1810.06951/) (2018)
- [Deep Metric Learning with Angular Loss](https://mlsanity.com/paper/1708.01682/) (2017)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Learning Deep Embeddings with Histogram Loss](https://mlsanity.com/paper/1611.00822/) (2016)
- [Deep Fingerprinting: Undermining Website Fingerprinting Defenses with Deep Learning](https://mlsanity.com/paper/1801.02265/) (2018)
- [k-fingerprinting: a Robust Scalable Website Fingerprinting Technique](https://mlsanity.com/paper/1509.00789/) (2015)
- [Automated Website Fingerprinting through Deep Learning](https://mlsanity.com/paper/1708.06376/) (2017)
- [Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification](https://mlsanity.com/paper/1612.02814/) (2016)
- [Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning](https://mlsanity.com/paper/1802.10215/) (2018)
- [Tik-Tok: The Utility of Packet Timing in Website Fingerprinting Attacks](https://mlsanity.com/paper/1902.06421/) (2019)
- [Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic](https://mlsanity.com/paper/2309.04798/) (2023)
- [Rethinking preventing class-collapsing in metric learning with margin-based losses](https://mlsanity.com/paper/2006.05162/) (2020)
- [Realistic Website Fingerprinting By Augmenting Network Trace](https://mlsanity.com/paper/2309.10147/) (2023)
- [Toward an Efficient Website Fingerprinting Defense](https://mlsanity.com/paper/1512.00524/) (2015)
- [Few-Shot Website Fingerprinting Attack](https://mlsanity.com/paper/2101.10063/) (2021)
- [Towards Effective and Efficient Padding Machines for Tor](https://mlsanity.com/paper/2011.13471/) (2020)

## Built on by (most cited first, 3 of 3)

- [STAR: Semantic-Traffic Alignment and Retrieval for Zero-Shot HTTPS Website Fingerprinting](https://mlsanity.com/paper/2512.17667/) (2025)
- [Attack Smarter: Attention-Driven Fine-Grained Webpage Fingerprinting Attacks](https://mlsanity.com/paper/2506.20082/) (2025)
- [Beyond a Single Perspective: Towards a Realistic Evaluation of Website Fingerprinting Attacks](https://mlsanity.com/paper/2510.14283/) (2025)

## Abstract (arXiv)

Website Fingerprinting (WF) attacks can effectively identify the websites visited by Tor clients via analyzing encrypted traffic patterns. Existing attacks focus on identifying different websites, but their accuracy dramatically decreases when applied to identify fine-grained webpages, especially when distinguishing among different subpages of the same website. WebPage Fingerprinting (WPF) attacks face the challenges of highly similar traffic patterns and a much larger scale of webpages. Furthermore, clients often visit multiple webpages concurrently, increasing the difficulty of extracting the traffic patterns of each webpage from the obfuscated traffic. In this paper, we propose Oscar, a WPF attack based on multi-label metric learning that identifies different webpages from obfuscated traffic by transforming the feature space. Oscar can extract the subtle differences among various webpages, even those with similar traffic patterns. In particular, Oscar combines proxy-based and sample-based metric learning losses to extract webpage features from obfuscated traffic and identify multiple webpages. We prototype Oscar and evaluate its performance using traffic collected from 1,000 monitored webpages and over 9,000 unmonitored webpages in the real world. Oscar demonstrates an 88.6% improvement in the multi-label metric Recall@5 compared to the state-of-the-art attacks.