PROJECT TITLE :

MADAM: Effective and Efficient Behavior-based Android Malware Detection and Prevention - 2018

ABSTRACT:

Android users are constantly threatened by an increasing variety of malicious applications (apps), generically known as malware. Malware constitutes a serious threat to user privacy, money, device and file integrity. During this Project we have a tendency to note that, by learning their actions, we tend to will classify malware into a tiny variety of behavioral classes, each of that performs a limited set of misbehaviors that characterize them. These misbehaviors will be defined by monitoring features belonging to totally different Android levels. In this Project we tend to present MADAM, a completely unique host-based mostly malware detection system for Android devices which simultaneously analyzes and correlates features at four levels: kernel, application, user and package, to detect and stop malicious behaviors. MADAM has been specifically designed to require under consideration those behaviors that are characteristics of almost each real malware which can be found in the wild. MADAM detects and effectively blocks more than ninety six p.c of malicious apps, that return from three massive datasets with concerning 2,80zero apps, by exploiting the cooperation of 2 parallel classifiers and a behavioral signature-primarily based detector. Intensive experiments, that conjointly includes the analysis of a testbed of 9,804 real apps, are conducted to point out the low false alarm rate, the negligible performance overhead and restricted battery consumption.