FG-SAT: Efficient Flow Graph for Encrypted Traffic Classification Under Environment Shifts

FG-SAT: эффективный граф потоков для классификации зашифрованного трафика в условиях сдвига среды
Dongqi Han, Baoxu Liu, Zhigang Lü, Susu Cui, Zhiliang Wang, Xueying Han, Bo Jiang, Weihang Wang
2025-01-01

Flow GraphGraphSATJensen-Shannon divergenceencrypted traffic classificationenvironment shifts
Encrypted traffic classification plays a critical role in network security and management. Currently, mining deep patterns from side-channel contents and plaintext fields through neural networks is a major solution. However, existing methods have two major limitations: (1) They fail to recognize the critical link between transport layer mechanisms and applications, missing the opportunity to learn internal structure features for accurate traffic classification. (2) They assume network traffic in an unrealistically stable and singular environment, making it difficult to effectively classify real-world traffic under environment shifts. In this paper, we propose FG-SAT, the first end-to-end method for encrypted traffic analysis under environment shifts. We propose a key abstraction, theFlow Graph, to represent flow internal relationship structures and rich node attributes, which enables robust and generalized representation. Additionally, to address the problem of inconsistent data distribution under environment shifts, we introduce a novel feature selection algorithm based on Jensen-Shannon divergence (JSD) to select robust node attributes. Finally, we design a classifier, GraphSAT, which integrates Graph-SAGE and GAT to deeply learn Flow Graph features, enabling accurate encrypted traffic identification. FG-SAT exhibits both efficient and robust classification performance under environment shifts and outperforms state-of-the-art methods in encrypted attack detection and application classification.
1
A Jensen-Shannon divergence-based feature selection algorithm identifies node attributes that remain robust under inconsistent data distributions caused by environment shifts.
2
FG-SAT achieves efficient and robust classification under environment shifts and outperforms state-of-the-art methods in encrypted attack detection and application classification.
3
FG-SAT is presented as an end-to-end encrypted traffic classification method designed specifically for network environment shifts.
4
The GraphSAT classifier combines Graph-SAGE and graph attention networks to learn Flow Graph features for encrypted traffic identification.
5
The proposed Flow Graph models internal relationships between transport-layer mechanisms and applications while incorporating rich node attributes for robust traffic representation.

encrypted network traffic under environment shifts

robust and efficient traffic classification, including encrypted attack detection and application identification, across shifting data distributions

Publication Details
Publication Date
2025-01-01
Journal
Publisher
ISSN
Cited by
28
Access Type
Author Information
Authors
Dongqi Han
Baoxu Liu
Zhigang Lü
Susu Cui
Zhiliang Wang
Xueying Han
Bo Jiang
Weihang Wang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%