An Ensemble Learning Based Block-Chain Framework-Enabled Collaborative Intrusion Detection

Abstract

Significant research has been done on combining intrusion detection with blockchain to increase data privacy and identify ongoing and upcoming cyberattacks. These method makes use of learning-based ensemble methods to assist in the identification of complex hazardous events while at the same time maintaining the confidentiality of the data. These models may also be used to provide additional privacy and security assurances during the live migration of virtual machines (VMs) to the cloud. As a result of this, virtual machines could be moved between data centres or cloud service providers in a safe and prompt manner. In this paper, a Deep Block-chain Framework (DBF) is suggested. The goal of the DBF is to create a privacy-based blockchain that includes smart contracts & security-based centralized intrusion detection. When dealing with sequential network data utilizing the UNSW-NB15 datasets, an ensemble learning approach is used for the purpose of detecting intrusions.