Sahal, Abdirashid AhmedAlam, ShahidSogukpinar, Ibrahim2025-01-062025-01-062018978-153867893-010.1109/UBMK.2018.85665102-s2.0-85060625431https://doi.org/10.1109/UBMK.2018.8566510https://hdl.handle.net/20.500.14669/13643rd International Conference on Computer Science and Engineering, UBMK 2018 -- 20 September 2018 through 23 September 2018 -- Sarajevo -- 143560Due to the open app distribution and more than two billion active users, Android platform continues to serve as low-hanging fruit for malware developers. According to the McAfee threat report, the number of malware families found in the Google Play increased by 30% in 2017. Permission-based access control model is one of the most important mechanisms to protect Android apps against malware. In this paper, we propose a new permission-based model that enhances the efficiency and accuracy of Android malware analysis and detection, and has the capability of potentially detecting previously unknown malware. In this new model, we improve the feature selection by introducing a new weighting method, named TF-IDFCF, based on the class frequency (CF) of the feature. The results of our experiments show that our proposed method has a detection rate of greater than 95.3% with a low false positive rate, when tested with different classifiers. © 2018 IEEE.eninfo:eu-repo/semantics/closedAccessAndroidMachine LearningMalware Analysis and DetectionPermissionsTF-IDFConference Object268264