Intrusion Detection for IoT Environments Through Side-Channel and Machine Learning Techniques
Alejandro Domínguez Campos, Felipe Lemus-Prieto, José‐Luis González‐Sánchez, Andrés Caro Lindo · IEEE Access · 2024
The rise of the Internet of Things (IoT) technology during the past decade has resulted in multiple applications in many different fields. Some of the data processed using this technology can be specially sensitive, and the devices involved can be prone to cyberattacks, which has resulted in a rising interest in the field of information security applied to IoT. This study presents a method for analyzing an IoT network to detect attacks using side-channel techniques that monitor the power usage of the devices. We show that it is possible to employ a monitoring system powered by Machine Learning to detect intrusions without interfering with the normal behavior of the devices. Our tests yield positive results under different scenarios, such as using a custom dataset, detecting new attacks that the model was not trained with, or detecting attacks as they happen live. The main advantages of our proposed system are its simplicity, its reproducibility (both code and data are made available) and portability, since it can be deployed on many devices and does not have a high demand of resources. We propose different deployment strategies, depending on the structure of the IoT network and the power constraints of the devices.