An Automated Permission Selection Framework for Android Platform
- PDF / 1,866,308 Bytes
- 15 Pages / 547.044 x 736.903 pts Page_size
- 91 Downloads / 246 Views
An Automated Permission Selection Framework for Android Platform Toqeer Ali · Yasar Khan · Tamleek Ali · Safiullah Faizullah · Turki Alghamdi · Sajid Anwar
Received: 30 May 2018 / Accepted: 23 July 2018 © Springer Nature B.V. 2018
Abstract Enhancements to Android security frameworks have been a focal point of the research community in the past few years due to Android’s growing popularity. The Android permission framework performs a vital role in identifying the malicious behavior of an application. Most malware utilizes the wrong permission, given by an application that exploits device security and privacy. The focus point should be managing the permission given to an application at the very beginning, when installing the application.
T. Ali () · S. Faizullah · T. Alghamdi Faculty of Computer and Information System, Isalmic University of Madinah, Madinah, Saudi Arabia e-mail: [email protected] S. Faizullah e-mail: [email protected] T. Alghamdi e-mail: [email protected] Y. Khan Malaysian Institute of Information Technology, Universiti Kuala Lumpur, Kuala Lumpur, Malaysia e-mail: [email protected] T. Ali · S. Anwar Institute of Management Sceinces, Peshawar, Pakistan T. Ali e-mail: [email protected] S. Anwar e-mail: [email protected]
However, in this regard, the solutions given so far are user-centric. That means the user needs to decide whether permission should be given or not. A novice user usually ignores the warnings during installation of an app or accessing a resource. In this research, we introduce an enhanced Android permission framework that automatically decides for the user which permissions should be given to application at installation or when resources are accessed in the newer Android versions. We generated a large dataset of permissions and their ratings to generate a machine learning model. Finally, an incorporated machine learning model automatically decides on behalf of a user which permissions should be given to the user. Our results show high accuracy in the auto-selection of suggested permissions for the end user. Keywords Android · Android permisions · Android security · Smartphone security · Operating system · Machine learning
1 Introduction Smartphones’ capabilities and their computational power have been increasing rapidly and consistently over the last decade. To better utilize these resources, different software stacks were introduced by various vendors during this period. Among these, Android is the most efficient, powerful, and customizable open
T. Ali et al.
source operating system (OS) available in the market. The free source code availability attracts a large number of developers to create applications for the next generation of platforms. Android offers the basic functionality of middleware in the form of a virtual machine (VM), system utilities, and some basic applications like a dialer, clock, alarm, browsers, etc. To extend functionality, third-party developers create applications with new ideas and better features. These applications are th
Data Loading...
