Leaking personal information on mobile devices is a serious problem. Work on information leak detection for mobile devices, until now, mostly focus on action within a single application, while the coordinated action of several applications for the malicious purpose is becoming popular. This study proposes a hybrid approach that combines static and dynamic analysis to detect information leak as a result of the coordinated action of multiple applications. In this text, we call it inter-application malware. The analysis takes place in two stages. In the first stage, we use static analysis to determine the chains of sensitive actions on multiple applications. The chain of sensitive actions is the sequential user’s actions that may lead to information leakage. In the second stage, we validate whether the chain of sensitive actions indeed leaks user’s data by using the dynamic analysis. In fact, the applications in question are forced to execute after the chains of sensitive actions detected in the first stage. We monitor the sensitive actions to determine which actions make information leak. In order to do so, we modify the Android Emulator to trigger and monitor any action of any applications running on it. We have evaluated our tool, namely eDSDroid, on the famous Toyapps test case. The test result shows the correctness and effectiveness of our tool.
