Context-aware multi-agent based framework for securing Android

With the proliferation of mobile devices, and bring-your-own-device policies of corporations, securing mobile devices from malware based on context information has become paramount, more so with possible context-aware malware threats. Android is one of the most popular operating system for such mobile devices. Given the availability of multiple sensors on Android mobile devices that can be accessed by Android applications using Android API; and the lack of available on-device resources such as battery, memory and CPU; we propose the use of a context-aware multi-agent based framework to monitor and dynamically launch investigative agents on Android mobile devices. We provide a framework design, implementation details and initial evaluation of our proposed framework to show that a multi-agent based system is a viable option for securing such devices. We propose the use of spatial context-information gathered using location information(GPS, network) and device context (battery level, Android API level, rooted device) to make context-aware decisions for the framework. We also show that we can use context information to reduce frequency of network connections and CPU utilization overhead caused by the Multi-Agent framework.