DEMUX: Boundary-Aware Multi-Scale Traffic Demixing for Multi-Tab Website Fingerprinting

TL;DR

DEMUX is a boundary-aware, multi-scale traffic demixing framework that significantly improves multi-tab website fingerprinting accuracy by addressing structural challenges with novel components.

Contribution

It introduces a comprehensive framework with boundary-preserving aggregation, multi-scale CNN, and transformer modules to effectively demix interleaved traffic in multi-tab scenarios.

Findings

DEMUX achieves state-of-the-art accuracy in multi-tab fingerprinting.

In the 5-tab setting, DEMUX attains P@5 of 0.943 and MAP@5 of 0.961.

Boundary preserving aggregation improves baseline performance without architectural changes.

Abstract

Website fingerprinting (WF) attacks infer the websites visited by users from encrypted traffic in anonymous networks such as Tor. Existing deep learning methods achieve high accuracy under the single-tab assumption but degrade substantially when users open multiple tabs concurrently, producing interleaved traffic that transforms WF into an implicit demixing problem. We identify three structural requirements for effective multi-tab demixing, namely signal integrity at segment boundaries, multi-scale local modeling, and relative temporal association of dispersed fragments, and show that no prior method satisfies all three simultaneously. We propose DEMUX, a designed framework that addresses these requirements through three tightly coupled components. A Boundary Preserving Aggregation Module employs overlapping window partitioning with joint packet-level and burst-level feature extraction. A Multi-Scale Parallel CNN captures heterogeneous temporal patterns via parallel branches. A two-stage Transformer encoder with Rotary Positional Embedding enables robust cross-window fragment association. The Boundary Preserving Aggregation Module additionally serves as a plug-and-play preprocessor that consistently improves existing baselines without architectural modification. Extensive experiments across closed-world, open-world, defense-augmented, dynamic-tab, and cross-configuration settings demonstrate that DEMUX achieves state-of-the-art performance. In the challenging closed-world 5-tab setting, DEMUX attains a P@5 of 0.943 and MAP@5 of 0.961, outperforming the strongest baseline by 9.2 and 6.2 percentage points respectively, confirming its strong robustness in complex multi-tab demixing scenarios.