A Machine Learning Approach for Automated Malware Detection

S. Lavanya , MS. K. Muthukarupaee , B. Lavanya , K. Mahalakshmi , R. Sowmya

Malware Detection, Machine Learning, XGBoost, Portable Executable, Feature Engineering, Explainable AI, SHAP, Static Analysis, Cybersecurity, Threat Intelligence.

This paper presents an automated malware detection system that leverages the XGBoost machine learning algorithm to classify executable (.exe) files as Malicious or Benign. The proposed framework integrates Portable Executable (PE) attribute extraction, automated preprocessing, feature engineering, and Explainable AI (XAI) to deliver transparent and actionable threat intelligence. PE attributes are extracted using the pefile library, normalised, and transformed into structured feature vectors for classification. The XGBoost classifier achieves high detection accuracy by capturing complex interactions among PE features, outperforming conventional signature-based approaches against novel and polymorphic malware. An integrated XAI module employing SHAP values highlights the most influential PE attributes driving each classification decision, fostering analyst trust. The system further automates risk level assignment and generates comprehensive threat reports with mitigation recommendations via a Flask-based web application. Experimental results confirm accurate detection of both known and previously unseen malware variants, demonstrating the efficacy of the proposed pipeline as a scalable, interpretable, and deployable cybersecurity solution.

Published Paper   E-Certificate

"A Machine Learning Approach for Automated Malware Detection", JETNR - JOURNAL OF EMERGING TRENDS AND NOVEL RESEARCH (www.JETNR.org), ISSN:2984-9276, Vol.4, Issue 6, page no.c506-c516, June-2026, Available :https://rjpn.org/JETNR/papers/JETNR2606283.pdf

Volume 4 Issue 6, June-2026

Pages : c506-c516

Paper Reg. ID: JETNR_235344

Published Paper Id: JETNR2606283

Downloads: 00048

Research Area: Science and Technology

Country: Tiruchirappalli, Tamil Nadu, India

Published Paper PDF: https://rjpn.org/JETNR/papers/JETNR2606283

Published Paper URL: https://rjpn.org/JETNR/viewpaperforall?paper=JETNR2606283

ISSN: 2984-9276 | IMPACT FACTOR: 9.87 Calculated By Google Scholar | ESTD YEAR: 2023

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.87 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: RJPN (IJPublication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition