Intrusion Detection and Classification using Deep Learning and Nature Inspired Optimization for IOT Based Network

Abstract

The Internet of Things (IoT) has rapidly developed and, accordingly, opened the door for more cyber-attacks due to the increase in the number of connected devices and the amount of sensitive data transmitted over these networks. Classic Intrusion Detection Systems (IDS) are unable to recognize threats that are coming in newly created ways since they cannot analyze the different traffic patterns well. The proposed intelligent intrusion detection framework integrates Deep Learning (DL) with nature-inspired optimization for efficient attack classification. The Hybrid CNN–LSTM deep architecture is designed to extract and learn temporal and spatial features of the network traffic, while “Particle Swarm Optimization (PSO)” and “Ant Colony Optimization (ACO)” are used for optimal feature selection and dimensionality reduction on the UNSW-NB15 dataset. The results of this study show that the optimization process not only greatly improves the classification accuracy but also saves a lot of time in computations. The Hybrid CNN-LSTM model obtains a binary accuracy of 0.948, which is coupled with 0.948 for precision, recall, and F1-score. Additionally, it surpasses CNN and LSTM models used separately. In multiclass prediction, the hybrid method claims 0.720 accuracy, 0.510 precision, and 0.680 recall, thus showing a considerable improvement in the detection of varied IoT attacks.