EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HybFusion: A holistic Android malware detection framework with advanced feature fusion and ensemble learning

Vu Minh Manh iD, Cho Do Xuan, Nguyen Thi Khanh Van

PLOS One · 12.06.2026 · 21 (6) · e0349589

DOI: 10.1371/journal.pone.0349589 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.06.2026. Verfasst von Vu Minh Manh und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Security, Posts and Telecommunications Institute of Technology, Hanoi, Vietnam. Hauptthemen laut MEDLINE: Ensemble Learning, Mobile Applications, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PhD Scholarship Programme of Vingroup Innovation Foundation (VINIF), VinUniversity.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Android malware detection remains a critical challenge due to the rapid increase in malware variants and the growing sophistication of obfuscation techniques. To address these issues, this paper introduces HybFusion, a holistic Android malware detection framework that integrates advanced feature fusion with ensemble learning to enhance detection effectiveness and reduce false positives. HybFusion combines two complementary feature types to overcome the limitations of existing methods in capturing a comprehensive representation of malware behaviors and semantics: (1) behavioral features extracted from the function call graph and embedded using the Graph Isomorphism Network, and (2) semantic permission features obtained from the AndroidManifest.xml file by applying a normalization process to convert permission identifiers into a permission sequence, which is then embedded using a lightweight pre-trained Transformer-based language model. This strategy enables better leveraging of semantic relationships among permissions while maintaining low computational cost. In addition, HybFusion adopts a stacking-based ensemble learning strategy that leverages the strengths of multiple classifiers to further improve detection robustness. Extensive experimental results demonstrate that HybFusion outperforms existing approaches across all evaluation metrics, achieving a recall of 99.24% and an F1-score of 99.27%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ensemble LearningMobile ApplicationsSoftwareAlgorithmsSemantics

Autor:innen und Institutionen

  • Faculty of Information Security, Posts and Telecommunications Institute of Technology, Hanoi, Vietnam.
  • Lab Blockchain, Faculty of Information Security, Posts and Telecommunications Institute of Technology, Hanoi, Vietnam.
  • Faculty of Information Technology, Posts and Telecommunications Institute of Technology, Hanoi, Vietnam.

ORCID-Profile: Vu Minh Manh

Förderung

  • PhD Scholarship Programme of Vingroup Innovation Foundation (VINIF), VinUniversity

Zitieren

APA

Minh Manh, V., Do Xuan, C., & Van, N. T. K. (2026). HybFusion: A holistic Android malware detection framework with advanced feature fusion and ensemble learning. PLOS One, 21(6), e0349589. https://doi.org/10.1371/journal.pone.0349589

Vancouver

Minh Manh V, Do Xuan C, Van NTK. HybFusion: A holistic Android malware detection framework with advanced feature fusion and ensemble learning. PLOS One. 2026;21(6):e0349589. doi:10.1371/journal.pone.0349589

BibTeX
@article{MinhManh2026,
  author = {Minh Manh, Vu and Do Xuan, Cho and Van, Nguyen Thi Khanh},
  title = {HybFusion: A holistic Android malware detection framework with advanced feature fusion and ensemble learning},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0349589},
  doi = {10.1371/journal.pone.0349589}
}
Kostenlos starten →