Malware detection based on deep learning approach in cloud computing Available to Purchase

The problem of ensuring security and resilience in a cloud platform is of utmost importance and complexity due to the proliferation of several unique applications that rely on shared resources. It is imperative for the cloud infrastructure to incorporate a robust security analysis system capable of effectively detecting and mitigating potential hazards and malware threats. Machine learning-driven malware analysis has received much attention, but its computational complexity and detection precision are constrained. This study suggested a fresh malware detection system. We employed Independent Component Analysis (ICA) and Decision Tree (TD) data mining techniques to extract key features from the malware dataset at low dimensions’ rate. The experimental outcomes for input clusters for deep learning models using clustering methods then demonstrate improved classification accuracy and False Positive Rate (FPR).