Securing Confidential Information in Big Data Based on Cognitive Artificial Intelligence and Machine Learning

Abstract

The high demand for handling big data along with the current vulnerabilities of contemporary computer systems has made the world in need of a better cybersecurity system with high performance. Furthermore, confidential information is, most likely, combined with bulky non-confidential data. Yet, the encryption process of big data consumes a lot of resources and severely burdens the system's performance. This paper presents the architecture of a novel approach that encompasses Cognitive Artificial Intelligence and Machine Learning Methodology for Securing Sensitive Information (CAIMLSSI) in Big Data to overcome both vulnerabilities and performance issues. We describe the details of each module of the architecture, discuss validation issues, and present the mathematical analysis that shows the robustness of CAIMLSSI.