Research on Improving capabilities of effective android malware detection through Machine learning techniques

Computer Engineering

Now a days, drastically increased android smartphone users. Mobile apps become part of our everyday life, many of the services are provided to us through mobile apps. Therefore Android devices are the most targeted devices by malware because of their high popularity. So that it is necessary to provide Security to android device. To protect our data from malicious software, we need to detect malware from devices. Malware detection is process of detecting an unknown software and application from android device and giving security to the device. There are various ways to attack malicious program on device and previously harmful software can be detect by antivirus software but some traditional anti-virus systems are fail to classify strange malware between their correspondent families then according to realize current kinds on malware programs. So malware detection is necessary to detect malware and protect data. In this paper, we analyse the different malware detection techniques and their comparative studies. To improve malware detection accuracy, Hybrid analysis of malware and use Boosting, decision tree and support vector machine algorithm and also use ensemble learning of this three algorithm using voting classifier used in proposed model. We propose an algorithm through which we can increase the accuracy and other parameter so users get more security of personal information data.

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