Detecting android malware using an improved filter based technique in embedded software

Abstract

The technological advancements have led to evolution of sophisticated devices called smartphones. By providing extensive capabilities, they are becoming more and more popular. The Android based smartphones are preferred furthermore, due to their open-source nature. This has also led to the development of large number of malwares targeting these smartphones. Thus to protect the devices, some countermeasures are needed. Machine learning methods have gained popularity in detection of malware. This work proposes a malware detection technique in Android devices based on static analysis carried out using the Manifest files extracted from the apk files. The feature selection is performed using the proposed KNN based Relief algorithm and detection of malware is done using the proposed optimized SVM algorithm. The proposed method achieves a True Positive Rate greater than 0.70 and much reduced False Positive Rate values were obtained, with the values of False Positive Rate being very close to zero. The proposed KNN based feature selection is found to select better features in comparison with some popular existing feature selection techniques. The proposed optimized SVM technique achieves a performance that is on par with the performance of Neural Networks.