Abstract
The rapid adoption of Android devices comes with the growing prevalence of mobile malware, which leads to serious threats to mobile phone security and attacks private information on mobile devices. In this paper, we designed and implemented a model for malware detection on Android devices to protect private and financial information, for the mobile applications of the ATISCOM project. This model is based on client/server architecture, to reduce the heavy computations on a mobile device by sending data from the mobile device to the server for remote processing (i.e., offloading) of the predictions. We then gradually optimized our proposed model for better classification of the newly installed applications on Android devices. We at first adopted Naive Bayes to build the model with 92.4486% accuracy, then the classification method that gave the best accuracy of 93.85% for stochastic gradient descent (SGD) with binary class (i.e., malware and benign), and finally the regression method with numerical values ranging from −100 to 100 to manage the uncertainty predictions. Therefore, our proposed model with random forest regression gives a good accuracy in terms of performance, with a good correlation coefficient, minimum computation time and the smallest number of errors for malware detection.
Highlights
Nowadays, mobile devices are becoming an essential part of our daily life and are used even more than conventional computer systems such as personal computers
In our previous publication [16], we presented our proposed model for malware detection on Android devices based on client/server architecture to reduce the heavy computation of data on the mobile device and doing the processing remotely on the server, but we focused on the mobile device part by directly performing the tests offline on the device
We proposed a prediction model to secure mobile payment applications on Android devices based on client/server architecture to palliate the heavy computational load on mobile devices for malware detection
Summary
Mobile devices are becoming an essential part of our daily life and are used even more than conventional computer systems such as personal computers. To overcome the shortcomings of Bouncer and Play Protect, as well as to protect themselves from applications of unknown sources, several vendors of antivirus for Android smartphones are distributed, as free or premium versions, for individuals (e.g., Lookout) or businesses (e.g., MI:RIAM by Wandera, z9Engine by Zimperium, Skycure by Symantec) [5,6,7,8] These antiviruses do not always indicate the method used. Describe the client/server architecture and the remote processing (offloading) on the server for prediction of the newly installed applications to reduce the computation time on the mobile device, and by using numerical values for classification (i.e., −100 for benign and 100 for malware) to manage the uncertainty predictions; Implement our proposed model for malware detection to validate our proposed methodology; Detail the Naive Bayes method and present the results of more classification and regression algorithms from the Waikato environment for knowledge analysis (Weka).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
