Efficient feature selection analysis for accuracy malware classification

Rahiwan Nazar, Romli and Mohamad Fadli, Zolkipli and Mohd Zamri, Osman (2021) Efficient feature selection analysis for accuracy malware classification. In: Journal of Physics: Conference Series; 7th International Conference on Mathematics, Science, and Education 2020, ICMSE 2020, 6 October 2020 , Semarang, Virtual. pp. 1-9., 1918 (4). ISSN 1742-6588 (print); 1742-6596 (online)

Pdf (Open access)
Efficient feature selection analysis for accuracy malware classification.pdf
Available under License Creative Commons Attribution.

Download (734kB) | Preview


Android is designed for mobile devices and its open-source software. The growth and popularity of android platform are high compared to another platform. Due to its glory, the number of malware has been increasing exponentially. Android system used a permission mechanism to allow users and developers to manage their access to private information, system resources, and data storage required by Android applications (apps). It became an advantage to an attacker to violent the data. This paper proposes a novel framework for Android malware detection. Our framework used three major methods for effective feature representation on malware detection and used this method to classify malware and benign. The result demonstrates that the Random forest is with 23 features is more accurate detection than the other machine learning algorithm.

Item Type: Conference or Workshop Item (Lecture)
Additional Information: Indexed by Scopus
Uncontrolled Keywords: Android applications; Android platforms; Efficient feature selections
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Faculty of Computing
Depositing User: Mrs Norsaini Abdul Samat
Date Deposited: 11 Feb 2022 07:18
Last Modified: 11 Feb 2022 07:18
URI: http://umpir.ump.edu.my/id/eprint/31984
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item