Malware detection based on permissions on android platform using data mining

Joint Authors

Barhum, Tawfiq S.
Nasman, Muhammad I.

Source

المؤتمر الدولي حول المدن الذكية : آفاق و حلول، 30-31 أغسطس 2016

Publisher

Islamic University of Gaza Faculty of Engineering

Publication Date

2016-08-31

Country of Publication

Palestine (Gaza Strip)

No. of Pages

8

Main Subjects

Engineering & Technology Sciences (Multidisciplinary)

English Abstract

With the spreading of smart mobile devices to nearly every person, android operating system is dominating the mobile’s operating systems.

due to the weak policy of submitting application to google play store, attackers developed malware to attack the users of the Android operating system with malware application or by including malicious code into applications.

Researchers have been done in this area, but solutions required installing the applications to monitor the malware behavior, or by taking actions after installing the application .We proposed a new method using data mining to detect newly and unknown malware using the applications’ permissions as base features.

In order to create binary dataset we collected up to “103” benign and malware android app samples, the dataset consist of five different features collected based on different number of attributes and conditions.

Different evaluation measure used to evaluate the proposed method, the results show that we achieved 96.74 % with f-measure and 0.993 with area under the ROC curve..

Data Type

Conference Papers

Record ID

BIM-775857

• APA
• MLA
• AMA