Abstract
The Internet of Things (IoT) grew in popularity in recent years, becoming a crucial component of industrial, residential, and telecommunication applications, among others. This innovative idea promotes communication between physical components, such as sensors and actuators, to improve process flexibility and efficiency. Smart gadgets in IoT contexts interact using various message protocols. Message queuing telemetry transfer (MQTT) is a protocol that is used extensively in the IoT context to deliver sensor or event data. The aim of the proposed system is to create an intrusion detection system based on an artificial intelligence algorithm, which is becoming essential in the defense of the IoT networks against cybersecurity threats. This study proposes using a k-nearest neighbors (KNN) algorithm, linear discriminant analysis (LDA), a convolutional neural network (CNN), and a convolutional long short-term memory neural network (CNN-LSTM) to identify MQTT protocol IoT intrusions. A cybersecurity system based on artificial intelligence algorithms was examined and evaluated using a standard dataset retrieved from the Kaggle repository. The dataset was injected by five attacks, namely brute-force, flooding, malformed packet, SlowITe, and normal packets. The deep learning algorithm achieved high performance compared with the developing security system using machine learning algorithms. The performance accuracy of the KNN method was 80.82%, while the accuracy of the LDA algorithm was 76.60%. The CNN-LSTM model attained a high level of precision (98.94%) and is thus very effective at detecting intrusions in IoT settings.