Ensemble classification based hybrid dual-channel convolution neural network (dccnn) with enhanced manta ray foraging optimization (emrfo) algorithm for cyber security malware threats detection

Abstract

Introduction: this study suggests usage of hybrid deep learning (DL) for identifying malwares in Internet of Things (IoT) networks. Furthermore, Channel Boost STM-RENet (CB-STM-RENet) is proposed as a DCCNN optimization technique that extends the split-change-merge model. Malware detection is performed using Hybrid Dual Channel Convolutional Neural Network (DCCNN) and Manta Ray Forage Optimization. Methods: in this context, introduce a single-block convolutional STM known as DCCNN in CB-STM-RENet that performs local and spatial processing at the same time. The systematic use of the region and the deployment of parallel socialization processes facilitate the investigation of the unity of the region, the diversity of forces and the defining characteristics of the region. Three versions of DL: STM-RENet, DenseNet201 and InceptionResNetV2 (IRNV2) are proposed which work together to optimize DCCNN using split-change-merge in a unique way to improve generalization Hybrid learning. This dataset is a Google Code Jam (GCJ) for IoT malware detection challenges. Results: the experimental results of the suggested method are better than existing methods for obtained accuracies and values of precision, specificity, F1 scores, MCC, and avg. processing times in classifications of cyber threats