A Lightweight Intrusion Detection System Using Convolutional Neural Network and Long Short-Term Memory in Fog Computing

The Internet of Things (IoT) links various devices to digital services and significantly improves the quality of our lives. However, as IoT connectivity is growing rapidly, so do the risks of network vulnerabilities and threats. Many interesting Intrusion Detection Systems (IDSs) are presented based on machine learning (ML) techniques to overcome this problem. Given the resource limitations of fog computing environments, a lightweight IDS is essential. This paper introduces a hybrid deep learning (DL) method that combines convolutional neural networks (CNN) and long short-term memory (LSTM) to build an energy-aware, anomaly-based IDS. We test this system on a recent dataset, focusing on reducing overhead while maintaining high accuracy and a low false alarm rate. We compare CICIoT2023, KDD-99 and NSL-KDD datasets to evaluate the performance of the proposed IDS model based on key metrics, including latency, energy consumption, false alarm rate and detection rate metrics. Our findings show an accuracy rate over 92% and a false alarm rate below 0.38%. These results demonstrate that our system provides strong security without excessive resource use. The practicality of deploying IDS with limited resources is demonstrated by the successful implementation of IDS functionality on a Raspberry Pi acting as a Fog node. The proposed lightweight model, with a maximum power consumption of 6.12 W, demonstrates its potential to operate effectively on energy-limited devices such as low-power fog nodes or edge devices. We prioritize energy efficiency while maintaining high accuracy, distinguishing our scheme from existing approaches. Extensive experiments demonstrate a significant reduction in false positives, ensuring accurate identification of genuine security threats while minimizing unnecessary alerts.