MT-DEGCL: Multi-Task Encrypted Traffic Classification With Dual Embedding and Graph Contrastive Learning
- 12 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2220-2235
Abstract
Although encryption offers strong anonymity, it also facilitates the concealment of malicious activities, allowing adversaries to evade detection, and posing a great challenge to cybersecurity surveillance. Many existing encrypted traffic classification methods struggle to integrate flow- and packet-level tasks effectively, as they are trained independently, which is redundancy. Additionally, packet header and payload are treated equally, leading to the rich information in raw bytes remains fully unexplored, particularly in the abundant payload data. Moreover, they neglect the semantic invariance and common features between data samples, which ultimately results in suboptimal performance. To address these challenges, we propose an effective Multi-Task model using Dual Embedding and Graph Contrastive Learning (MT-DEGCL). Based on the byte-packet-flow structure of network traffic, a parallel dual embedding embeds the header and payload separately, followed by a cross-gated feature fusion strategy to capture the strong local packet-level representation. Then, we construct the traffic interaction graph and further utilize graph contrastive learning to extract the robust global flow-level representation. Finally, a multi-task model is trained for joint flow- and packet-level classification, leveraging the complementary learning between tasks to enhance overall performance. The experimental results on four real datasets highlight the effectiveness of MT-DEGCL, demonstrating superior performance in both tasks. Specifically, on the ISCX-Tor dataset, MT-DEGCL achieves F1 scores of 98.63% for flow-level classification and 98.10% at the packet level, surpassing the state-of-the-art (i.e., DE-GNN) by 2.03% and 83.21%, respectively. Furthermore, MT-DEGCL maximizes the rich information in raw payload bytes, significantly reducing or even nearly eliminating classification loss when using only payload data.Keywords
Funding Information
- National Natural Science Foundation of China (U24B20147)
- Major Science and Technology Special Project of Sichuan Province (2025ZDZX0059)
- Major Science and Technology Special Project of Sichuan Province (2026YFHZ0121)
- Major Science and Technology Special Project of Sichuan Province (2024ZDZX0044)
- Major Science and Technology Special Project of Sichuan Province (2024ZHCG0195)
This publication has 50 references indexed in Scilit:
- DE-GNN: Dual embedding with graph neural network for fine-grained encrypted traffic classificationComputer Networks, 2024
- FastTraffic: A lightweight method for encrypted traffic fast classificationComputer Networks, 2023
- TCGNN: Packet-grained network traffic classification via Graph Neural NetworksEngineering Applications of Artificial Intelligence, 2023
- Tor network traffic classification using machine learning based on time-related featureIET Conference Proceedings, 2023
- SFIM: Identify user behavior based on stable featuresPeer-to-Peer Networking and Applications, 2021
- TSCRNN: A novel classification scheme of encrypted traffic based on flow spatiotemporal features for efficient management of IIoTComputer Networks, 2021
- Toward effective mobile encrypted traffic classification through deep learningNeurocomputing, 2020
- A review on machine learning–based approaches for Internet traffic classificationAnnals of Telecommunications, 2020
- MIMETIC: Mobile encrypted traffic classification using multimodal deep learningComputer Networks, 2019
- Deep packet: a novel approach for encrypted traffic classification using deep learningSoft Computing, 2019