Maldroid Dynamic Malware Detection using Random Forest Algorithm
Gowtham Sethupathi1, Swapnil Siddharth2, Vikash Kumar3, Pratyush Kumar4, Ashwani Yadav5
1Gowtham Sethupathi, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India
2Swapnil Siddharth, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India
3Vikash Kumar, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India
4Pratyush Kumar, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India
5Ashwani Yadav, Department of Computer Science & Engineering, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 311-315 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3576048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Android platform has become one of the most widely used operating system for smart-phones with the number of users increasing day by day. The number of applications made for Android is also rising. Consequently, with the advantages of the apps, malware tend to come into the scene with an opportunity to harm the operating system as well as steal sensitive data available on the phone. To address a solution to this problem, a number of static and dynamic analysis tools and techniques have been introduced to distinguish between millions of Android apps in the marketplace and malicious apps. In this paper we study the benign Android apps, mine the pattern to classify benign apps from malicious apps. We also create an automated malware detection system, Maldroid, a program to find if an application is malicious or not. The program was tested with a large dataset of around benign apps and malicious app. Experimental results show that Maldroid is capable of detecting malware with relatively high F1 score of 98 percent.
Keyword: Android Applications, Malware Detection, Permission- Related APIs, Random Forests, Software Security.
Scope of the Article: Approximation and Randomized Algorithms