.png){kind=icon}
.png){kind=icon}
Return
Adaptive context-aware multi-tab website fingerprinting using hierarchical deep learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jnca.2025.104374.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Most existing models assume single-tab browsing, overlooking the real-world complexity of multi-tab scenarios. • Few models incorporate both contextual browsing behavior and dynamic adaptation. As a result, their ability to handle overlapping traffic flows and tab-switching patterns remains limited. • We propose a novel website fingerprinting framework designed to dynamically adapt to an unknown and variable number of concurrent tabs. • The proposed model consists of three core components: A Contextual Browsing Behavior Analysis Module (CBAM), a Dynamic Tab Adaptation Module (DTAM), and a Hierarchical Multi-Level Feature Extraction (HMLFE) module. • The proposed model approach integrates CBAM, DTAM, and HMLFE modules to dynamically adapt to varying numbers of active tabs while capturing contextual browsing behaviors.
Journal
IF:
8
Papers:
3.6K
Citations:
1.1W