Implementing Lightweight Intrusion Detection System on Resource Constrained Devices

The rapid growth of Internet of Things (IoT) devices has increased the risk of network intrusions, which need effective security solutions for devices with low computational capability. However, Deep Learning based Intrusion Detection Systems (IDS) often demand substantial computational resources, which are unsuitable for the resource constrained IoT devices. To tackle this issue, we propose a lightweight IDS for Raspberry Pi operation. The proposed architecture includes traffic capture, threat detection, and alerting modules, utilizing signature and anomaly-based techniques. The signature-based module detects known attacks using predefined patterns, while the machine learning-based anomaly detection module identifies new threats by monitoring deviations from normal network behavior. The evaluation results show that our proposed scheme can detect a wide range of threats with minimal computational overhead.