Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Journal of Advanced Research in Applied Sciences and Engineering TechnologyOpen Access

Benchmarking Classical and Deep Learning Models for Ransomware Detection Using Static PE Features

View Full Paper
Ask AI
Bookmark
Share

Authors

SWShuaib Ahmed WadhoYAYichiet AunMGMing-Lee Gan

Discussion

Loading...

Member takes

Overview

Analysis compares performance of machine learning and deep learning models on ransomware detection, indicating classical methods excel with static features.

Key Points

  • Tree ensemble methods such as Random Forest and XGBoost achieved near-perfect detection of ransomware.
  • Performance metrics including accuracy, precision, and F1 score demonstrated classical models outperform deep learning approaches.
  • Comprehensive data preprocessing and stratified cross-validation were key methodologies employed in this analysis.
  • Results suggest that while deep learning methods have higher computational costs, they provide no significant performance advantage over classical models.

Cite This Study

Wadho et al. (2025) studied this question.

synapsesocial.com/papers/68c1d60654b1d3bfb60f95b2https://doi.org/10.37934/araset.55.1.226235
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine Learning-Based Static Ransomware Detection Using PE Header Features and SHAP Interpretation2026
  2. 2Ransomware Detection Using Machine Learning Techniques2024 · 2 citations
  3. 3Ransomware Early Detection using Machine Learning Approach and Pre-Encryption Boundary Identification2024 · 8 citations
  4. 4Ransomware Detection Using Portable Executable Imports2024 · 1 citations
  5. 5Ransomware Detection by Machine Learning2025