A Novel Lightweight IoT Intrusion Detection Model Based on Self-Knowledge Distillation

The Internet of Things (IoT) environment contains many different types of devices, each with different functionalities, communication protocols, and security capabilities, which makes the IoT a complex challenge for security protection. Therefore, network intrusion detection (NID) is needed to detect intrusions in the network to secure the IoT. In recent years, deep learning (DL)-based intrusion detection systems have achieved excellent results, but they tend to require high-computational resources and storage space, which is not feasible for most IoT devices. In this article, we propose a lightweight intrusion detection model based on self-knowledge distillation (SKD), namely, tied block convolution lightweight deep neural network (TBCLNN), which improves the detection accuracy while also reducing the number of model parameters and computational cost. Specifically, we use the binary Harris Hawk optimization algorithm (bHHO) for dimensionality reduction of traffic features. We use lightweight convolution, such as tied block convolution (TBC), to design lightweight neural network (LNN) models with residual and inverse residual structures. Moreover, we propose an improved SKD loss function to solve the sample imbalance problem and compensate for the performance degradation caused by lightweight neural networks. The multiclassification accuracy of our proposed method exceeds 99% on all three publicly available IoT datasets. The experimental results show that our method has a small model size and requires only low-computational resources, making it suitable for resource-constrained IoT intrusion detection.