Android Malware Detection Using Machine Learning with Feature Selection Based on the Genetic Algorithm

Jaehyeong Lee, Hyuk Jang, Sungmin Ha and Yourim Yoon
Additional contact information
Jaehyeong Lee: Department of Computer Engineering, Gachon University, 1342 Seongnamdaero, Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Korea
Hyuk Jang: Department of Computer Engineering, Gachon University, 1342 Seongnamdaero, Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Korea
Sungmin Ha: Department of Business Administration, Gachon University, 1342 Seongnamdaero, Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Korea
Yourim Yoon: Department of Computer Engineering, Gachon University, 1342 Seongnamdaero, Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Korea

Mathematics, 2021, vol. 9, issue 21, 1-20

Abstract: Since the discovery that machine learning can be used to effectively detect Android malware, many studies on machine learning-based malware detection techniques have been conducted. Several methods based on feature selection, particularly genetic algorithms, have been proposed to increase the performance and reduce costs. However, because they have yet to be compared with other methods and their many features have not been sufficiently verified, such methods have certain limitations. This study investigates whether genetic algorithm-based feature selection helps Android malware detection. We applied nine machine learning algorithms with genetic algorithm-based feature selection for 1104 static features through 5000 benign applications and 2500 malwares included in the Andro-AutoPsy dataset. Comparative experimental results show that the genetic algorithm performed better than the information gain-based method, which is generally used as a feature selection method. Moreover, machine learning using the proposed genetic algorithm-based feature selection has an absolute advantage in terms of time compared to machine learning without feature selection. The results indicate that incorporating genetic algorithms into Android malware detection is a valuable approach. Furthermore, to improve malware detection performance, it is useful to apply genetic algorithm-based feature selection to machine learning.

Keywords: android malware detection; machine learning; genetic algorithm; feature selection; static analysis (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2227-7390/9/21/2813/pdf (application/pdf)
https://www.mdpi.com/2227-7390/9/21/2813/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:9:y:2021:i:21:p:2813-:d:673305

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().