Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 4, 2026Journal of Cybersecurity and PrivacyOpen Access

Machine Learning-Based Static Ransomware Detection Using PE Header Features and SHAP Interpretation

View Full Paper
Ask AI
Bookmark
Share

Authors

GBGabryella BarnesUniversity of North GeorgiaAGAhmad Ghafarian

Discussion

Loading...

Member takes

Implication

This work investigates ransomware detection using machine learning in static environments, highlighting implications for cybersecurity.

Key Points

  • The research aims to evaluate the effectiveness of static detection methods for ransomware using PE header features.
  • Implemented an end-to-end machine learning pipeline.
  • Conducted experiments on three binary classification problems: ransomware vs. benign, malware vs. benign, and ransomware vs. other malware.
  • Utilized Random Forest, Support Vector Machine, and XGBoost models.
  • Employed SHAP to analyze feature contributions and performance issues.
  • XGBoost demonstrated strong performance on structurally distinct class boundaries.
  • Tree-based ensemble models struggled with fine-grained discrimination among similar malware types.
  • Static PE header analysis showed potential but had limitations in detailed ransomware detection.

Cite This Study

Barnes et al. (2026) studied this question.

synapsesocial.com/papers/69d0af1c659487ece0fa506chttps://doi.org/10.3390/jcp6020058
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. 1Zero-Ran Sniff: A zero-day ransomware early detection method based on zero-shot learning2024 · 48 citations
  2. 2Zero-Day Ransomware Attack Detection Using Static Portable Executable Header Features2025 · 3 citations
  3. 3A Method of Malware Detection Using Machine Learning Algorithm2025 · 1 citations
  4. 4A novel machine learning approach for detecting first-time-appeared malware2024 · 61 citations
  5. 5Matplotlib: A 2D Graphics Environment2007 · 40,950 citations