Poster Abstract: Detecting Abnormalities in IoT Program Executions through Control-Flow-Based Features

The Internet of Things (IoT) has penetrated various domains, from smart grids to precision agriculture, facilitating remote sensing and control. However, IoT devices are target to a spectrum of reliability and security issues. Therefore, capturing the normal behavior of these devices and detecting abnormalities in program execution is key for reliable deployment. However, existing program anomaly detection techniques that use either flow-sensitive or context-sensitive information only capture system call context and therefore have limited detection scope and accuracy. Control-flow information generated on these devices can capture the paths taken during program execution. In this poster abstract, we propose using context-sensitive features based on control-flow and discuss their effectiveness in detecting anomalous behavior.