Machine Learning Inspired Phishing Detection (PD) for Efficient Classification and Secure Storage Distribution (SSD) for Cloud-IoT Application

Abstract

Cloud-IoT data security and privacy have become a major problem due to its sensitivity, which curbs multiple cloud applications. In addition, if the encrypted data lives in one place, in many fields, such as the financial industry and government agencies, the man-in-the-middle-attack (MMA) and phishing attack (PA) may have chances of realising the extraction. The phishing goal is evaluated and predicted by most previous machine learning models through a discrete or continuous result. The current models lag in accurately determining both attacks because of this approach. We developed a three-step phishing detection (PD) framework inspired by machine learning and a secure storage distribution (SSD) for cloud to improve model accuracy and storage security. The partition-based selection of features is designed for phishing detection (PD) with a hybrid classifier approach and hyper-parameter classifier tuning. Initially, the entire data set is partitioned by entropy and is hybridised for each performing model partition. In order to reduce the complexity, the next entropy is applied to decrease the dimension of each partition. Finally, to improve precision, the performing model is optimised with hyper-parameter tuning. The partition-based feature choice with the hybrid classifier approach outperforms with 97.86% accuracy for both attack detection from the experimental and comparative results of SVM, LM, NN and RF. Atlast, SSD performance is evaluated against other storage models where SSD outperforms other models.