Bio-Inspired Computational Paradigm for Feature Investigation and Malware Detection: Interactive Analytics

Ahmad, Firdaus and Nor Badrul, Anuar and Mohd Faizal, Ab Razak and Sangaiah, Arun Kumar (2017) Bio-Inspired Computational Paradigm for Feature Investigation and Malware Detection: Interactive Analytics. Multimedia Tools and Applications. pp. 1-37. ISSN 1380-7501(print); 1573-7721(online). (Published)

[img] PDF
Bio-inspired computational paradigm for feature investigation and malware detection- interactive analytics.pdf - Published Version
Restricted to Repository staff only

Download (2MB) | Request a copy
[img]
Preview
PDF
Bio-inspired computational paradigm for feature investigation and malware detection- interactive analytics 1.pdf - Published Version

Download (179kB) | Preview

Abstract

Recently, people rely on mobile devices to conduct their daily fundamental activities. Simultaneously, most of the people prefer devices with Android operating system. As the demand expands, deceitful authors develop malware to compromise Android for private and money purposes. Consequently, security analysts have to conduct static and dynamic analyses to counter malware violation. In this paper, we adopt static analysis which only requests minimal resource consumption and rapid processing. However, finding a minimum set of features in the static analysis are vital because it removes irrelevant data, reduces the runtime of machine learning detection and reduces the dimensionality of datasets. Therefore, in this paper, we investigate three categories of features, which are permissions, directory path, and telephony. This investigation considers the features frequency as well as repeatedly used in each application. Subsequently, this study evaluates the proposed features in three bio-inspired machine learning classifiers in artificial neural network (ANN) category to signify the usefulness of ANN type in uncovering unknown malware. The classifiers are multilayer perceptron (MLP), voted perceptron (VP) and radial basis function network (RBFN). Among all these three classifiers, the outstanding outcomes acquire is the MLP, which achieves 90% in accuracy and 87% in true positive rate (TPR), as well as 97% accuracy in our Bio Analyzer prediction system.

Item Type: Article
Uncontrolled Keywords: Static analysis; Malware; Feature selection; Android; Machine learning; Neural network
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Mrs. Neng Sury Sulaiman
Date Deposited: 21 Jul 2017 01:35
Last Modified: 21 Jul 2017 01:35
URI: http://umpir.ump.edu.my/id/eprint/17481
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item