A Novel Approach for IoT Intrusion Detection System using Modified Optimizer and Convolutional Neural Network

The development of cyber security is very important, and as a result, it has received a significant amount of research interest from academic institutions and industrial groups all over the globe. It is also of the utmost importance to offer computing that is environmentally friendly for the Internet of Things. In order to detect intrusions and identify malicious actors, machine learning algorithms play an essential part in the cyber security of the internet of things (IoT). Because of this, the purpose of this work is to create novel techniques of extracting attributes that take use of the benefits offered by swarm intelligence (SI) method. We devise a technique for the extracting the attributes that is based on the traditional neural networks. In addition, in order to compute the effectiveness of the IDS method that was created, four well recognized public datasets were employed. We also evaluated detailed comparisons to many alternative optimization approaches in order to test the proposed method's ability to compete successfully in the market. The findings demonstrate that the created strategy performs very well when measured against a variety of assessment metrics.