Improved Cultural Gray Wolf Optimizer with Deep Learning Enabled Ransomware Recognition and Classification on IoT Environment

In recent times, a massive development in the Internet of Things (IoT) and digital enhance in programmed devices are supporting malware producers to aim of IoT devices. The typical security performances against malware can be impossible because of minimal computing power for large-scale data in IoT platforms. The malware counts and its variations are enhancing because of nonstop malware attacks. Therefore, the efficiency development in malware investigation is vital necessity for stopping quick development of malicious attacks in IoT platforms. In this study, an Improved Cultural Gray Wolf Optimizer with Deep Learning Enabled Ransomware Recognition and Classification (ICGWODL-RRC) approach is proposed in the IoT atmosphere. The major intention of the ICGWODL-RRC approach is in the proper detection and classification of ransomware. The ICGWODL-RRC model follows a two-stage process. At first, the ICGWODL-RRC model includes gated recurrent unit (GRU) mechanism for detecting and classifying ransomware. The stimulation analysis of the ICGWODL-RRC methodology is investigated on the ransomware dataset. The comprehensive set of simulations indicates the advanced achievement of the ICGWODL-RRC methodology over present approaches.