Enormous numbers of mobile health applications (mHealth apps) developed recently on mobile devices (e.g. smart-phones, tablets, etc.) have enabled health status (e.g. sleep quality, heart rate, etc.) monitoring that is readily accessible to average mobile device users. Typically, such mHealth apps involve active usage of mobile device resources, such as on-board sensors, network bandwidth, etc. The rapid increase of these applications prompted the US FDA agency to put in place regulations on mHealth app risk assessment. But these existing and upcoming regulations have not yet been accompanied by a mobile auditing framework, which provides real-time monitoring of mHealth apps’ resource usage and triggers alerts to users if abnormal resource usage patterns are detected.
In this project, we develop a mobile auditing framework shown in the figure to the left (mAuditor Framework). The mAuditor runs as a separate process along with mHealth apps and other general purpose apps (e.g. Facebook, Gmail, etc.). The mAuditor consists of the profiler and the analyzer. The profiler collects the system trace and parse the trace if needed. The parsed trace is utilized by the analyzer, which analyzes the resource usage patterns and compare them with predefined configurations. mAuditor with its low-overhead and non-obtrusive design, monitors mHealth apps’ resource usage patterns in real-time and triggers alerts to users if abnormal resource usage patterns are detected.
This work is being spearheaded by Haiming Jin and supported by his colleagues at UIUC, Ting-yu Wang and Klara Nahrstedt.