Dwarf Mongoose Optimization with Machine-Learning-Driven Ransomware Detection in Internet of Things Environment

The internet of things (ransomware refers to a type malware) is the concept connecting devices and objects all types on internet. IoT cybersecurity task protecting ecosystems gadgets from cyber threats. Currently, ransomware serious threat challenging computing environment, which needs instant attention avoid moral financial blackmail. Thus, there comes real need for novel technique that can identify stop this kind attack. Several earlier detection techniques followed dynamic analysis method including complex process. However, takes long period time processing analysis, during malicious payload often sent. This study presents new model dwarf mongoose optimization with machine-learning-driven (DWOML-RWD). presented DWOML-RWD was mainly developed recognition classification goodware/ransomware. In technique, feature selection process initially carried out using an enhanced krill herd (EKHO) algorithm by use oppositional-based learning (QOBL). For detection, DWO extreme machine (ELM) classifier be utilized. design aids in optimal parameter ELM model. experimental validation examined benchmark dataset. results highlight superiority over other approaches.