WCSE

A Novel Method of Android Malware Detection Based on Ensemble Learning Algorithm

Abstract— Android is popular for mobile devices in recent years. As the risk of malware is sharply increasing in Android platform, Android malware detection has become an important research topic. However, the current work shows that the detection of malware still needs to be reformed. Many current results suggest a modification of permissions or a combination of permissions and intents, but Android's fragmentation issues and requiring rooting, hindering the widespread adoption of those methods. Many approaches have been proposed to detect this attack by modifying the Android OS. Existing anti-viruses depend on signature databases that need to be updated from time to time and are unable to detect zero-day malware. The Android Operating system allows inter-application communication through the use of component reuse by using intents. A malware detection model is developed based on ensemble learning algorithms and on the basis of the random forest in WEKA. The method we proposed can take a better efficiency and precision.

Index Terms— Android Malware, Ensemble Learning, Random Forest, Classification

Jingyi Zhao
Tianjin Intelligent Computing and Software New Technology Key Laboratory, School of computer Science and Engineering, Tianjin University of Technology, CHINA
Xiuliang Mo
Tianjin Intelligent Computing and Software New Technology Key Laboratory, School of computer Science and Engineering, Tianjin University of Technology, CHINA
Qiao Zheng
Tianjin Intelligent Computing and Software New Technology Key Laboratory, School of computer Science and Engineering, Tianjin University of Technology, CHINA

[Download]

Cite: Jingyi Zhao, Xiuliang Mo, Qiao Zheng, "A Novel Method of Android Malware Detection Based on Ensemble Learning Algorithm," Proceedings of 2018 the 8th International Workshop on Computer Science and Engineering, pp. 531-538, Bangkok, 28-30 June, 2018.