Towards Android Malware Detection using Intelligent Agents

New opportunities for malicious applications take advantage of the openness of the Android platform. Malwares use intelligent and new approaches to compromise Android mobile devices. One example is a mobile botnet that can control smartphones and steal user data by misusing Android features such as Short Message Service (SMS). Multi-agent technology is a powerful tool that can monitor certain environments and detect abnormal behaviour in order to protect user data. In this paper, we propose an Android user profiling framework that employs a multi-agent system to observe Android mobile devices and interact with a central server in order to detect malicious applications and SMS botnet activity on Android mobile devices. We developed an intelligent and proactive framework that scans incoming and outgoing text messages, monitors Android resources and observes user usage, including connectivity time, with the aim of creating a user profile that will help to perform behaviour analysis on the detected malicious and suspicious SMS messages.