A framework for Android Malware detection and classification
Muhammad Murtaz, Hassan Azwar, Syed Baqir Ali, Saad Ur Rehman · 2018
Currently the android platform is that the quickest growing hand-held OS package. And it's become the foremost desirable and viable objective of malevolent applications. Android malware growth has been increasing dramatically in conjunction with increasing the variety and guiltiness of their developing techniques. Mobile malware is therefore pernicious and, on the increase, consequently having a quick and reliable detection system is important for the users. Subtle Android malware use detection shunning techniques so as to cover their malicious activities from analysis tools. During this analysis, a brand-new detection and characterization system for investigation significant deviations within the network behaviour of a smart-phone application is planned. The most goal of the planned system is to guard mobile device users and cellular infrastructure corporations from malicious applications simply nine traffic feature measurements. The planned system isn't solely ready to observe the malicious or masquerading apps, however may also determine them as general malware or specific malware (i.e. adware) on a mobile device. The planned methodology showed the common accuracy 94% for 5 classifiers namely; Random Forest (RF), K-Nearest Neighbour (KNN), decision Tree (DT), Random Tree (RT) and Regression (R) etc. We have a tendency to conjointly provide a tagged dataset of mobile malware traffic with a lot of applications includes benign and twelve completely different families of each adware and general malware. Recent substantial analysis on machine learning algorithms analyse options from mischievous application and use those preferences to catalogue and discover unknown malicious applications. This study condenses the progression of malware detection techniques supported machine learning algorithms centred on the Android Operating systems.