Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices

TL;DR

This paper presents lightweight machine learning models, including decision trees and neural networks, for real-time intrusion detection on resource-constrained IoT microcontrollers, achieving high accuracy while conserving memory.

Contribution

It introduces resource-efficient, on-device intrusion detection models tailored for microcontrollers, balancing accuracy and computational demands.

Findings

Decision tree achieves 99% detection accuracy.

Neural network achieves 96% detection accuracy.

Both models are suitable for real-time IoT security on microcontrollers.

Abstract

IoT devices particularly microcontrollers are challenged by their inherent limitations in processing capabilities, memory capacity, and energy conservation. Securing communication within IoT networks is further complicated by the heterogeneity of devices and the myriad of potential security threats. Our study introduces a lightweight model that utilises machine learning algorithms to achieve a notable detection accuracy of 99% using a decision tree method and 96% using a neural network in identifying cyber threats, including Denial of Service and Man-in-the-Middle attacks which make up the majority of the attacks these devices face. While the decision tree method offers higher accuracy, it requires more computational resources, whereas the neural network approach, despite a slightly lower accuracy, is more memory-efficient. Both methods enhance the real-time monitoring and defence of IoT networks, safeguarding the transmission of data. Additionally, our approach is tailored to conserve memory and optimise computational demands, rendering it suitable for deployment on microcontrollers with limited resources.