Data Quality IoT BoT Attack Detection using Progressive Learning Model

The Internet of Things’ development (IoT) devices in recent years has raised security concerns due to an increase in malicious traffic on a global scale. As smart devices based on IoT proliferate across several networks, so are the cybersecurity dangers associated with them. Big datasets like Bot-IoT, which train algorithms using machine learning on connections-based detection of intrusions for IoT devices, were created to help mitigate these dangers. Proper deployment of the Internet of Things (IoT) may bring about multiple advantages. It is a promising technology. For instance, Despite the fact that Internet of Things botnets have become a significant threat, there won’t be numerous full and meticulous studies evaluating the value of botnet detection methods in IoT applications. From these explanations, we developed a Conv1D-LSTM neural network for the predicting IoT BoT (Mirai, Gafgyt) attack. We also implemented a diverse. A variety of machine learning approaches involving as Logistic Regression, Random Forest and Support Vector Machine (SVM). Our analysis and experiments illustrate that our proposed neural network model can accurately classify the IoT BoT attack with 96.41%.