EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GSIDroid: A Suspicious Subgraph-Driven and Interpretable Android Malware Detection System

Hong Huang iD, Weitao Huang iD, Feng Jiang

Sensors · 01.07.2025 · 25 (13) · 4116

DOI: 10.3390/s25134116 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.07.2025. Verfasst von Hong Huang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory Project of Enterprise Informatization and IoT Measurement and Control Technology for Universities in Sichuan Province, Central Guidance for Local Science and Technology Development Fund Projects, Tibet Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the growing threat of Android malware has caused significant economic losses and posed serious risks to user security and privacy. Machine learning-based detection approaches have improved the accuracy of malware identification, thereby providing more effective protection for Android users. However, graph-based detection methods rely on whole-graph computations instead of subgraph-level analyses, and they often ignore the semantic information of individual nodes. Moreover, limited attention has been paid to the interpretability of these models, hindering a deeper understanding of malicious behaviors and restricting their utility in supporting cybersecurity professionals for further in-depth research. To address these challenges, we propose GSIDroid, a novel subgraph-driven and interpretable Android malware detection framework designed to enhance detection performance, reduce computational overhead, protect user security, and assist security experts in rigorous malware analysis. GSIDroid focuses on extracting suspicious subgraphs, integrating deep and shallow-semantic features with permission information, and incorporating both global and local interpretability modules to ensure transparent, trustworthy, and analyzable detection results. Experiments conducted on 14,520 samples demonstrate that GSIDroid achieves an F1 score of 97.14%, and its interpretability module successfully identifies critical nodes and permission features that influence detection decisions, thereby enhancing practical deployment and supporting further security research.

Schlagwörter

Stichwörter der Autor:innen

Android malware detectionexplainable machine learninggraph convolutional networksemantic information

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, China.
  • School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China.

ORCID-Profile: Hong Huang, Weitao Huang

Förderung

  • Key Laboratory Project of Enterprise Informatization and IoT Measurement and Control Technology for Universities in Sichuan Province
  • Central Guidance for Local Science and Technology Development Fund Projects
  • Tibet Science and Technology Program
  • Innovation Fund of Postgraduates at Sichuan University of Science & Engineering
  • Central Guidance for Local Science and Technology Development Fund Project
  • Innovation Fund of Postgraduates at Sichuan University of Science & Engineering

Zitieren

APA

Huang, H., Huang, W., & Jiang, F. (2025). GSIDroid: A Suspicious Subgraph-Driven and Interpretable Android Malware Detection System. Sensors, 25(13), 4116. https://doi.org/10.3390/s25134116

Vancouver

Huang H, Huang W, Jiang F. GSIDroid: A Suspicious Subgraph-Driven and Interpretable Android Malware Detection System. Sensors. 2025;25(13):4116. doi:10.3390/s25134116

BibTeX
@article{Huang2025,
  author = {Huang, Hong and Huang, Weitao and Jiang, Feng},
  title = {GSIDroid: A Suspicious Subgraph-Driven and Interpretable Android Malware Detection System},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4116},
  doi = {10.3390/s25134116}
}
Kostenlos starten →