Classifying Android Malware Categories through Dynamic System Calls Ranked via ReliefF

DOI

10.2991/978-94-6463-740-3_6How to use a DOI?

Keywords

Android Security; Mobile Malware; Multi-Category Classification; Feature Ranking; Dynamic analysis

Abstract

Android’s popularity as an operating system stems from its extensive benefits; however, this has also made it a primary target for malware, which now exists in various categories. Numerous approaches leveraging static and dynamic analysis have been proposed for malware detection, though static analysis faces inherent limitations that dynamic analysis can address. Hence, this paper focuses on classifying malware categories—Adware, Fraudware, Ransomware, and Spyware—using dynamically extracted system call data. We employ the ReliefF algorithm for effective feature ranking and selection, aiming to achieve high detection accuracy with a minimal feature set. Experimental results reveal that an optimal subset of 70 system calls out of 289 achieves a peak accuracy of 94.50%, reducing the feature set by approximately 75.6%. Our findings demonstrate the efficacy of the dynamic approach in enhancing malware detection, providing a robust solution to the evolving mobile cybersecurity threat landscape.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yash Sharma
AU  - Anshul Arora
PY  - 2025
DA  - 2025/06/25
TI  - Classifying Android Malware Categories through Dynamic System Calls Ranked via ReliefF
BT  - Proceedings of the 6th International Conference on Deep Learning, Artificial Intelligence and Robotics (ICDLAIR 2024)
PB  - Atlantis Press
SP  - 53
EP  - 62
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-740-3_6
DO  - 10.2991/978-94-6463-740-3_6
ID  - Sharma2025
ER  -