EUVIMEDEUVIMED entdecken
Crossref

An Integrated Multi-Source Framework for Explainable Android Malware Detection with SOC Integration

Pallavi M. Shimpi, Nitin Namdeo Pise

Pertanika Journal of Science and Technology · 30.10.2026 · 34 (5)

DOI: 10.47836/pjst.34.5.10 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pertanika Journal of Science and Technology, online erschienen am 30.10.2026. Verfasst von Pallavi M. Shimpi und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neurosec Malware Scanner is an integrated malware-analysis framework that combines multi-source threat intelligence, static machine-learning classification, SHAP-based explainability, and Security Operations Centre (SOC)-oriented result presentation within a unified workflow. The system queries multiple file-hash threat-intelligence services in parallel and consolidates their outputs using a weighted aggregation mechanism. In parallel, a Python-based machine-learning pipeline extracts static malware features and evaluates four supervised classifiers: Random Forest, XGBoost, Gradient Boosting, and Logistic Regression. The framework is evaluated using five publicly available benchmark datasets: SOMLAP, TUANDROMD, Drebin, EMBER, and MH-100K. The best classification results obtained in the experiments are 99.6% on SOMLAP, 99.8% on TUANDROMD, 98.9% on Drebin, 94.3% on EMBER, and 86.7% on MH-100K. To improve interpretability, the framework incorporates SHAP-based explanations that identify the features contributing to individual model predictions. The system additionally employs cryptographic hashing, result caching, structured logging, and dashboard-based visualization to support repeatable malware-triage workflows. The proposed framework demonstrates the feasibility of integrating machine-learning detection, explainability, and threat-intelligence enrichment within an analyst-oriented malware-analysis pipeline. However, validation using recent real-world malware samples and deployment in operational SOC environments remains necessary to establish production-level effectiveness.

Zitieren

APA

Shimpi, P. M., & Pise, N. N. (2026). An Integrated Multi-Source Framework for Explainable Android Malware Detection with SOC Integration. Pertanika Journal of Science and Technology, 34(5). https://doi.org/10.47836/pjst.34.5.10

Vancouver

Shimpi PM, Pise NN. An Integrated Multi-Source Framework for Explainable Android Malware Detection with SOC Integration. Pertanika Journal of Science and Technology. 2026;34(5). doi:10.47836/pjst.34.5.10

BibTeX
@article{Shimpi2026,
  author = {Shimpi, Pallavi M. and Pise, Nitin Namdeo},
  title = {An Integrated Multi-Source Framework for Explainable Android Malware Detection with SOC Integration},
  journal = {Pertanika Journal of Science and Technology},
  year = {2026},
  volume = {34},
  number = {5},
  doi = {10.47836/pjst.34.5.10}
}
Kostenlos starten →