A novel encrypted traffic detection model based on detachable convolutional GCN-LSTM

Abstract With the widespread adoption of network encryption technologies, traditional detection methods increasingly struggle to identify malicious encrypted traffic due to their limited ability to capture structural and behavioral characteristics. To address this issue, this paper proposes a Detach...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaogang Yuan, Jianxin Wan, Dezhi An, Huan Pei
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-13397-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763267517349888
author Xiaogang Yuan
Jianxin Wan
Dezhi An
Huan Pei
author_facet Xiaogang Yuan
Jianxin Wan
Dezhi An
Huan Pei
author_sort Xiaogang Yuan
collection DOAJ
description Abstract With the widespread adoption of network encryption technologies, traditional detection methods increasingly struggle to identify malicious encrypted traffic due to their limited ability to capture structural and behavioral characteristics. To address this issue, this paper proposes a Detachable Convolutional GCN-LSTM (DC-GL) model. The proposed model constructs graph-structured data by integrating protocol-layer features and traffic statistical features extracted from encrypted flows. A Graph Convolutional Network (GCN) is employed to capture structural dependencies among nodes, while a Long Short-Term Memory (LSTM) network models the temporal dynamics of traffic behavior. To improve computational efficiency and feature extraction performance, detachable convolution is introduced into the GCN layers. In addition, an attention mechanism is incorporated to enhance the representation of critical features. Experimental results demonstrate that the DC-GL model outperforms several mainstream approaches in terms of accuracy, recall, and other key metrics, while also exhibiting faster convergence and greater robustness. These results suggest that DC-GL offers an effective and promising approach for malicious encrypted traffic detection.
format Article
id doaj-art-d0945153c9a34012b33f91cd4b23cde8
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d0945153c9a34012b33f91cd4b23cde82025-08-20T03:05:27ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-13397-2A novel encrypted traffic detection model based on detachable convolutional GCN-LSTMXiaogang Yuan0Jianxin Wan1Dezhi An2Huan Pei3School of Cyber Security, Gansu University of Political Science and LawSchool of Cyber Security, Gansu University of Political Science and LawSchool of Cyber Security, Gansu University of Political Science and LawSchool of Cyber Security, Gansu University of Political Science and LawAbstract With the widespread adoption of network encryption technologies, traditional detection methods increasingly struggle to identify malicious encrypted traffic due to their limited ability to capture structural and behavioral characteristics. To address this issue, this paper proposes a Detachable Convolutional GCN-LSTM (DC-GL) model. The proposed model constructs graph-structured data by integrating protocol-layer features and traffic statistical features extracted from encrypted flows. A Graph Convolutional Network (GCN) is employed to capture structural dependencies among nodes, while a Long Short-Term Memory (LSTM) network models the temporal dynamics of traffic behavior. To improve computational efficiency and feature extraction performance, detachable convolution is introduced into the GCN layers. In addition, an attention mechanism is incorporated to enhance the representation of critical features. Experimental results demonstrate that the DC-GL model outperforms several mainstream approaches in terms of accuracy, recall, and other key metrics, while also exhibiting faster convergence and greater robustness. These results suggest that DC-GL offers an effective and promising approach for malicious encrypted traffic detection.https://doi.org/10.1038/s41598-025-13397-2Malicious encrypted trafficIntrusion detectionDetachable convolutionGraph neural networkAttention mechanism
spellingShingle Xiaogang Yuan
Jianxin Wan
Dezhi An
Huan Pei
A novel encrypted traffic detection model based on detachable convolutional GCN-LSTM
Scientific Reports
Malicious encrypted traffic
Intrusion detection
Detachable convolution
Graph neural network
Attention mechanism
title A novel encrypted traffic detection model based on detachable convolutional GCN-LSTM
title_full A novel encrypted traffic detection model based on detachable convolutional GCN-LSTM
title_fullStr A novel encrypted traffic detection model based on detachable convolutional GCN-LSTM
title_full_unstemmed A novel encrypted traffic detection model based on detachable convolutional GCN-LSTM
title_short A novel encrypted traffic detection model based on detachable convolutional GCN-LSTM
title_sort novel encrypted traffic detection model based on detachable convolutional gcn lstm
topic Malicious encrypted traffic
Intrusion detection
Detachable convolution
Graph neural network
Attention mechanism
url https://doi.org/10.1038/s41598-025-13397-2
work_keys_str_mv AT xiaogangyuan anovelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm
AT jianxinwan anovelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm
AT dezhian anovelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm
AT huanpei anovelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm
AT xiaogangyuan novelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm
AT jianxinwan novelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm
AT dezhian novelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm
AT huanpei novelencryptedtrafficdetectionmodelbasedondetachableconvolutionalgcnlstm