Android Malware Detection Using Backpropagation Neural Network

Fais Al Huda, Wayan Firdaus Mahmudy, Herman Tolle


The rapid growing adoption of android operating system around the world affects the growth of malware that attacks this platform. One possible solution to overcome the threat of malware is building a comprehensive system to detect existing malware. This paper proposes multilayer perceptron artificial neural network trained with backpropagation algorithm to determine an application is malware or non-malware application which is often called benign application. The parameters that used in this study based on the list of permissions in the manifest file, the battery rating based on permission, and the size of the application file. Final weights obtained in the training phase will be used in mobile applications for malware detection. The experimental results show that the proposed method for detection of malware on android is effective. The effectiveness is demonstrated by the results of the accuracy of the system developed in this study is relatively high to recognize existing malware samples.


android manifest, classification, smartphone, static analysis

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics