There is Explosive increase in mobile application more and more threat, viruses and benign are migrate from traditional PC to mobile devices. Existence of this information and access creates more importance which makes device attractive targets for malicious entities. For this we proposed a probabilistic discriminative model which has regularized logistic regression for android malware detection with decompiled source code. There are so many approaches for detection of android malware has been proposed by using permission or source code analysis or dynamic analysis. In this survey paper, we use a probabilistic discriminative model for detection of malware by using supervised method. It also shows that probabilistic model based on regularized regression also it works well with permission. These three tools will give us complete part of analysis for the existing system which will gives us a complete part of analysis for exiting system. From this tool we get source code patterns. These patterns are studied and network database is train for getting malware and normal app signature.