Deep Learning Approaches for IoT Intrusion Detection Systems

Abstract

The Internet of Things (IoT) has had a substantial impact on a number of industries, including smart cities, the medical field, the automotive industry, and logistics tracking. But along with the IoT's advantages come security worries that are proliferating more and more. Deep learning-based Intelligent Network Intrusion Detection Systems (NIDS) have been created to detect continually evolving network threats and trends in order to address this issue. Six alternative deep learning algorithms, including CNN, RNN, and DNN architectures, are used in this research to present a novel anomaly-based solution for IoT networks. Three distinct intrusion detection datasets were used to evaluate the algorithms, and the findings revealed that the hybrid method performed better than the others in terms of accuracy. In particular, the hybrid algorithm had a 99.13% accuracy on the UNSW-NB15 dataset, an 89.01% accuracy on the IoTID20 dataset, and a 90.83% accuracy on the BoTNeTIoT-L01-v2 dataset. These results point to the suggested hybrid algorithm as superior to previous algorithms and a potential intrusion detection method for Internet of Things networks.