Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Malicious Network Behavior Detection Using Fusion of Packet Captures Files and Business Feature Data.

Mingshu He¹, Xiaojuan Wang¹, Lei Jin²

¹School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China.

Sensors (Basel, Switzerland)

|September 10, 2021

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Cross-disease immune cells atlas reveals the similarities and differences of cell characteristics and interactions in rheumatic diseases.

Frontiers in medicine·2026

Same author

The Role of Abatacept on Inflammation and Fibrosis in Hypochlorous Acid-Induced Fibrosis Mice.

International journal of rheumatic diseases·2025

Same author

Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing.

Sensors (Basel, Switzerland)·2025

Same author

ADAM Metallopeptidase domain 19 promotes skin fibrosis in systemic sclerosis via neuregulin-1.

Molecular medicine (Cambridge, Mass.)·2024

Same author

The role and mechanism of CRISPLD2 in skin fibrosis of systemic sclerosis.

Rheumatology (Oxford, England)·2024

Same author

Alternative splicing and intron retention: Their profiles and roles in cutaneous fibrosis of systemic sclerosis.

Journal of autoimmunity·2024

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

This summary is machine-generated.

This study introduces a novel fusion model using one-dimensional convolution to detect malicious network behavior by combining packet capture and business data. This approach enhances detection precision compared to single-data source methods.

Area of Science:

Cybersecurity
Machine Learning
Network Traffic Analysis

Background:

Information and communication technologies (ICT) are vital, but internet vulnerabilities enable malicious attacks.
Current machine learning (ML) and deep learning (DL) methods often rely on single data sources, limiting feature extraction.
Incomplete feature mining from single data sources can reduce the precision of malicious behavior detection.

Purpose of the Study:

To propose a novel fusion model for improved malicious network behavior detection.
To address the limitations of single-data source approaches in identifying cyber threats.
To enhance the precision of detecting malicious activities in network traffic.

Main Methods:

Developed a one-dimensional (1D) convolution-based fusion model.

Keywords:

convolution dimension data fusion malicious behavior detection network traffic

Related Experiment Videos

Integrated packet capture files and business feature data for analysis.

Evaluated early data fusion, feature fusion, and decision fusion strategies.

Main Results:

The proposed fusion model demonstrated improved malicious behavior detection results.
Fusion models outperformed single-data source models on network traffic and Internet of Things (IoT) datasets.
Early data fusion, feature fusion, and decision fusion were all found to be effective.

Conclusions:

The 1D convolution-based fusion model offers a more precise method for malicious network behavior detection.
Integrating diverse data sources significantly enhances the capability to identify cyber threats.
Further research can explore the adaptability of 1D and 2D convolution for network traffic data analysis.