SOMDROID: android malware detection by artificial neural network trained using unsupervised learning
- PDF / 7,047,112 Bytes
- 31 Pages / 595.276 x 790.866 pts Page_size
- 99 Downloads / 259 Views
RESEARCH PAPER
SOMDROID: android malware detection by artificial neural network trained using unsupervised learning Arvind Mahindru1,2 · A. L. Sangal1 Received: 29 April 2020 / Revised: 3 September 2020 / Accepted: 25 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Android has gained its popularity due to its open-source and number of freely available apps in its official play store. Appropriate functioning of Android apps depends upon the permission or set of permissions which an app demands at the time of installation and run-time. By taking the advantage of these permissions or set of permissions, cybercriminals are developing malware-infected apps daily. In this study, we proposed a framework named as “SOMDROID”, that work on the principle of unsupervised machine learning algorithm. To develop an effective and efficient Android malware detection model, we collect 5,00,000 distinct Android apps from promised repositories and extract 1844 unique features. Further, to select significant features or feature sets, we applied six different feature ranking approaches in this study. With the selected feature or feature sets, we implement the Self-Organizing Map (SOM) algorithm of Kohonen and measure four distinct performance parameters, i.e., Intra-cluster distance, Inter-cluster distance, Accuracy and F-measure. Empirical result reveals that our proposed framework is able to detect 98.7% malware that belongs to unknown families and in addition to that the detection rate is higher by 2% when compared to commercial anti-virus scanners and frameworks proposed in the literature. Keywords Android permissions · Self-organizing map · Intrusion–detection · Cyber security · Smartphone · API calls · Feature selection and android apps
1 Introduction Nowadays, mobile apps have become essential for the survival of human beings. To perform daily routine tasks, human beings interact with these installed apps on their smartphone. Daily, a number of new users install various apps in their smartphones to get a wealth of information. According to a report published online1 there are 3.50 billion users using smartphones worldwide. The Android operating system has gained its popularity due to its open nature and number of free apps in its official play store.2 As per the statics,3 there are 2.9 million apps * Arvind Mahindru [email protected] A. L. Sangal [email protected] 1
Department of Computer Science and Engineering, Dr. B.R. Ambedkar National Institute of Technology, Jalandhar 144011, India
Department of Computer Science and Applications, D.A.V. University, Sarmastpur, Jalandhar 144012, India
2
available in the official play store. Android apps depend upon the permission or set of permissions for its proper functioning. Android has given the privilege to the users to grant or revoke the permission at the time of installation. This facility was not present in the earlier version of Android. To prevent misuse of permission or set of permissions, Google has introduced this
Data Loading...