Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Perceived partner responsiveness between benign prostatic hyperplasia's symptom index and aging male symptoms.

Scientific reports·2026
Same author

Decent Work Mediates the Relationship Between Work Capital and Work Engagement Among Nurses.

Nursing open·2026
Same author

Kinematic Strategies of Dragonfly Free-Fall Recovery from an Asymmetric Body Roll.

Insects·2026
Same author

Corrigendum to "Dual-responsive drug delivery systems prepared by blend electrospinning" [Int. J. Pharm. 543(1-2) (2018) 1-7].

International journal of pharmaceutics·2026
Same author

Corrigendum to "Thermosensitive nanofibers loaded with ciprofloxacin as antibacterial wound dressing material" [Int. J. Pharm. 517(1-2) (2017) 135-147].

International journal of pharmaceutics·2026
Same author

Multi-Scale Water Modulation for Regulating Water Reactivity and Suppressing Nanoscale Zero-Valent Iron (nZVI) Corrosion.

Small (Weinheim an der Bergstrasse, Germany)·2026

Related Experiment Video

Updated: Jun 5, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Malicious DNS detection by combining improved transformer and CNN.

Heyu Li1, Zhangmeizhi Li2, Shuyan Zhang3

  • 1Admission Office Changchun Sci-Tech University, Changchun, 130600, China. lhy18844033000@sina.com.

Scientific Reports
|December 5, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces an improved Transformer and convolutional neural network model for detecting malicious domain servers. The novel approach significantly enhances accuracy and detection speed compared to traditional methods.

Keywords:
CNNMalicious DNS detectionMultiple attention mechanismNetwork securityTransformer

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

673

Related Experiment Videos

Last Updated: Jun 5, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

673

Area of Science:

  • Computer Science
  • Network Security
  • Artificial Intelligence

Background:

  • Network security threats are escalating with widespread internet use.
  • Domain name servers are critical infrastructure frequently targeted by attacks.
  • Traditional detection methods struggle with evolving threats due to manual effort and static rules.

Purpose of the Study:

  • To develop a more adaptive and efficient method for detecting malicious domain servers.
  • To overcome the limitations of traditional rule-based and feature-engineered approaches.
  • To enhance the accuracy and speed of malicious domain server identification.

Main Methods:

  • Improved Transformer model with adjusted attention heads and encoding.
  • Integration of the enhanced Transformer with convolutional neural networks.
  • Application of a block-based ensemble classifier for final detection.

Main Results:

  • Achieved an average accuracy score of 95.8%.
  • Demonstrated an average detection time score of 96.8%.
  • Showcased an average feature extraction ability score of 96.3% with an overall performance of 97.6%.

Conclusions:

  • The proposed method significantly outperforms traditional approaches in accuracy and detection time.
  • This novel technique offers a powerful new tool for identifying malicious domain servers.
  • The findings contribute to advancing network security defenses against sophisticated threats.