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 Experiment Video

Updated: Mar 6, 2026

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

2.7K

Application of representation learning in detecting botnet attacks.

Hieu Le Ngoc1

  • 1Faculty of Information Technology, Van Hien University, Ho Chi Minh City, Vietnam. hieuln@vhu.edu.vn.

Scientific Reports
|March 4, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same journal

Clinical crown height changes in mandibular anterior teeth retained with two types of fixed retainers over two years: findings from a randomized clinical trial.

Scientific reports·2026
Same journal

Rethinking water governance through indigenous systems: A comparative assessment of qanat and well irrigation productivity in Sabzevar County, Iran.

Scientific reports·2026
Same journal

Distributed Nash equilibrium seeking for second-order systems with finite/fixed-time convergence in the absence of velocity measurement.

Scientific reports·2026
Same journal

Determinants of pregnancy termination among ever-married women of reproductive age in Bangladesh.

Scientific reports·2026
Same journal

Occurrence and human health risk assessment of organochlorine pesticides in irrigated and non-irrigated agricultural soils of Wondogenet District, Ethiopia.

Scientific reports·2026
Same journal

High angular resolution diffusion imaging of neurodevelopment in children through data creation with deep learning.

Scientific reports·2026
See all related articles

This study introduces an advanced framework for robust botnet detection, utilizing novel feature engineering and representation learning. The method effectively identifies unseen botnet threats with high accuracy, improving cybersecurity defenses.

Area of Science:

  • Cybersecurity
  • Machine Learning
  • Network Security

Background:

  • Botnet detection is a persistent cybersecurity challenge.
  • Traditional methods struggle with novel threats due to poor generalization.
  • Existing approaches are often reactive and limited by manual feature engineering.

Purpose of the Study:

  • To develop a robust framework for enhanced botnet detection.
  • To overcome limitations of traditional methods, particularly generalization to unseen threats.
  • To improve the adaptability and resilience of intrusion detection systems.

Main Methods:

  • Implemented advanced feature engineering, including octet splitting for IP addresses.
  • Utilized Hilbert space-filling curve for network flow representation learning into 2D images.
Keywords:
Anomaly detectionBotnetCybersecurityDeep learningNetwork traffic analysisRepresentation learning

Related Experiment Videos

Last Updated: Mar 6, 2026

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

2.7K
  • Addressed class imbalance with SMOTE, weighted sampler, and Focal Loss.

    • Main Results:

    • Achieved 98.34% accuracy and 98.38% weighted F1-score on unseen botnet data.
    • Demonstrated superior generalization capabilities compared to traditional models.
    • Successfully detected novel botnet families in cross-scenario validation.

    Conclusions:

    • The proposed framework significantly enhances botnet detection accuracy and generalization.
    • Learned, spatially-aware representations outperform traditional models for detecting novel threats.
    • This work advances the development of adaptive and resilient intrusion detection systems.