Empirical Evaluation on Anomaly Behavior Detection for Low-Cost Micro-Controllers Utilizing Accurate Power Analysis

Since hardware/software vendors produce their IoT products easily and inexpensively, they often outsource their designs to third-party vendors where malicious third-party vendors can have a chance to insert software Trojans as well as 'hardware Trojans' into their IoT devices. How to tackle the issue becomes a serious concern these days. In this paper, we propose an anomaly behavior detection method utilizing accurate power analysis for low-cost micro-controllers. Our method accurately measures power consumption of the target device, and then classifies its waveform into the sleep-mode part, in which a micro-controller saves power, and into the active-mode part, in which a micro-controller works in a normal operation. After that, we obtain the duration time and consumed power from each active-mode period as feature values. Finally, we detect abnormal behavior based on the obtained feature values utilizing an outlier detection method. In our experiments, we empirically evaluate the proposed method utilizing two types of micro-controllers, and the experimental results demonstrate that our proposed method successfully detects abnormal behaviors.