Using probabilistic generative models for ranking risks of Android apps

摘要: One of Android's main defense mechanisms against malicious apps is a risk communication mechanism which, before user installs an app, warns the about permissions app requires, trusting that will make right decision. This approach has been shown to be ineffective as it presents information each in "tand-alone" ashion and way requires too much technical knowledge time distill useful information.We introduce notion scoring ranking for Android apps, improve identify three desiderata effective scheme. We propose use probabilistic generative models schemes, several such models, ranging from simple Naive Bayes, advanced hierarchical mixture models. Experimental results conducted using real-world datasets show general significantly outperform existing approaches, Bayes give promising approach.