<![CDATA[The rapid integration and application of the Internet of Things in daily life have significantly improved connectivity and intelligent control to various devices. However, it has exposed such systems to increased susceptibility to cyber challenges, such as infiltration, data sovereignty, and cyber-attacks. There is a need for an efficient and secure solution to these apparent security concerns which require complex social structures to adapt to various learning lessons quickly. The purpose of this study is to provide an inventive evolutionary operation to enhance the security of IoT networks and by integrating Convolutional Neural Networks and items of Grey Wolf Optimization algorithms – Standard GWO, Modified GWO and Advanced modified GWO. The GWOs were used to include surveillance accuracy layout, hence boosting detection accuracy. The action Lloyd testing found that smaller OWG intelligence (which achieved initially) unlimited interpretations which increased the percentage and was 97.4 %. This approach was further increased with FGWE, achieving 97.7 percentage, and 97.8 2.02% errors. The performance of both was 98.4 and 97.5 for the two classes, respectively. The current study’s results reveal the effectiveness of computational development to enhancing secure IoT networks and offer a secure prototype for potential study to optimize the security structure. effet for keynote curricular scenarios due to the system cause and trusty security solutions.]]>
