Open Access

ARTICLE

Adaptive Windowing with Label-Aware Attention for Robust Multi-Tab Website Fingerprinting

Chunqian Guo^*, Gang Chen

School of Cyberspace Security, Zhengzhou University, Zhengzhou, 450001, China

* Corresponding Author: Chunqian Guo. Email:

Computers, Materials & Continua 2026, 87(2), 31 https://doi.org/10.32604/cmc.2025.072184

Received 21 August 2025; Accepted 11 December 2025; Issue published 12 March 2026

Abstract

Despite the ability of the anonymous communication system The Onion Router (Tor) to obscure the content of communications, prior studies have shown that passive adversaries can still infer the websites visited by users through website fingerprinting (WF) attacks. Conventional WF methodologies demonstrate optimal performance in scenarios involving single-tab browsing. Conventional WF methods achieve optimal performance primarily in scenarios involving single-tab browsing. However, in real-world network environments, users often engage in multi-tab browsing, which generates overlapping traffic patterns from different websites. This overlap has been shown to significantly degrade the performance of classifiers that rely on the single-tab assumption. To address this challenge, this paper proposes a Transformer-based multi-tab website fingerprinting (MT-WF) attack framework. The model employs an adaptive sliding window mechanism to capture fine-grained features of traffic direction. Additionally, it incorporates a label-aware attention mechanism designed to dynamically separate and refine entangled traffic representations, enhancing the model’s ability to distinguish between overlapping traffic patterns. Furthermore, the model leverages global traffic patterns through multi-segment feature fusion and incorporates an incremental learning (IL) strategy to adapt to the continuously evolving website categories in open-world environments. Experimental results demonstrate that the proposed method achieves a top-2 precision of 0.78 in the closed-world setting. In the open-world scenario, the model attains an F1 score of 0.904, outperforming most existing baselines. The proposed method maintains superior performance even under challenging conditions, including WF defenses and concept drift.

---

Keywords

---