Conditional Autoregressive Value at Risk-Enabled Bird Swarm Algorithm and Intelligent Flawless Feature Selection Algorithm for Data Protection in Block chain

Abstract

The increasing expansion in the number of network users, security has become a difficult issue. This research utilizes a novel feature selection method, Conditional Autoregressive Value at Risk-enabled Bird Swarm Algorithm (CAViaR-BSA), which is a combination of CAViaR and BSA to obtain the best privacy-preserving coefficients. The rules required to choose the optimum and contributed features from the standard benchmark dataset are developed to enhance detection rate, a unique intrusion detection system is proposed. Intelligent Flawless Feature Selection Algorithm (IFLFSA) comprises of feature selection modules. The proposed algorithm is used to choose the best amount of attributes that will be most beneficial in detecting attacks. Several experiments are run on the KDD dataset to assess the proposed model. The proposed intrusion detection and feature selection system obtained 98.94% detection accuracy.