English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Encrypted traffic classification is receiving widespread attention fromresearchers and industrial companies. However, the existing methods onlyextract flow-level features, failing to handle short flows because ofunreliable statistical properties, or treat the header and payload equally,failing to mine the potential correlation between bytes. Therefore, in thispaper, we propose a byte-level traffic graph construction approach based onpoint-wise mutual information (PMI), and a model named Temporal Fusion Encoderusing Graph Neural Networks (TFE-GNN) for feature extraction. In particular, wedesign a dual embedding layer, a GNN-based traffic graph encoder as well as across-gated feature fusion mechanism, which can first embed the header andpayload bytes separately and then fuses them together to obtain a strongerfeature representation. The experimental results on two real datasetsdemonstrate that TFE-GNN outperforms multiple state-of-the-art methods infine-grained encrypted traffic classification tasks.

TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification