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 Videos

Optimizing cyberattack frequency forecasting by advanced machine learning adaptation with tumbling windows.

Song-Kyoo Kim1, Zeqiye Zhan2

  • 1Faculty of Applied Sciences, Macao Polytechnic University, R. de Luis Gonzaga Gomes, Macau, Macao. amang@mpu.edu.mo.

Scientific Reports
|July 1, 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 author

A Dataset on Public Bus Transportation during Normal and Grand Prix Seasons in the Macao Area.

Scientific dataยท2025
See all related articles

This study introduces a new method for long-term cyberattack prediction using Long Short-Term Memory (LSTM) networks. The approach enhances prediction accuracy and training efficiency for improved cybersecurity defenses.

Area of Science:

  • Cybersecurity
  • Machine Learning
  • Time Series Analysis

Background:

  • Current cyberattack detection primarily uses reactive methods, focusing on known signatures.
  • Less research addresses long-term cyberattack prediction, crucial for proactive defense strategies.

Purpose of the Study:

  • To develop and evaluate a novel methodology for long-term cyberattack prediction.
  • To improve prediction accuracy and training efficiency in cybersecurity.

Main Methods:

  • Utilizing Long Short-Term Memory (LSTM) networks for time series analysis.
  • Implementing flexible sliding window techniques for enhanced prediction.
  • Incorporating convolutional filters and bivariate performance measures.

Main Results:

Keywords:
Compact data learningConvolutional neural networkCyberattackCybersecurityForecastingMachine learningTumbling windows

Related Experiment Videos

  • The proposed methodology shows improved prediction outcomes.
  • Enhanced training efficiency was observed in the experiments.
  • The approach demonstrated potential for long-term cyberattack forecasting.

Conclusions:

  • The novel LSTM-based approach offers a valuable contribution to cyberattack prediction.
  • This research provides insights for developing advanced, long-term cybersecurity defense strategies.