A Deep Learning Driven Cloud Edge Intelligence Framework for Real-Time Big Data Based Cyber-Security Threat Detection

Purpose: This paper proposes a Secure Unified Data Model (UDM) Approach that enhances data security, trust, and reliability in Cyber-Physical Systems (CPS) by addressing data security risks such as breaches and unauthorized access. Methodology: The methodology involved several steps. Reviewing existing literature to understand the current state of data modeling in Cyber-Physical Systems (CPS) and identify potential vulnerabilities. Supported by threat modeling and risk assessment frameworks, it analyzed data security risks for the Unified Data Model (UDM) in CPS. The focus was on protecting the UDM through strong encryption, access controls, security training, and regular assessments, safeguarding data at rest and in transit. Findings: The findings show that a Secure Unified Data Model (UDM) approach improves data security in Cyber-Physical Systems (CPS) by strengthening access controls, encryption, and anomaly detection, thereby increasing CPS resilience against cyber threats. This promotes adoption in healthcare, smart cities, and governance. The secure UDM in CPS lowers breach risks, protects vendors and organizations, and offers scalable solutions that enhance productivity and reduce analytics costs. It supports safe data visualization, Business Intelligence (BI), and Artificial Intelligence (AI) tools, with potential applications in law enforcement for secure information sharing. The Secure UDM boosts trust, reliability, and compliance with data protection laws, encouraging adoption and innovation in critical sectors. Unique Contribution to Theory, Practice and Policy: involves developing a conceptual Secure UDM framework that combines access controls, encryption, and anomaly detection for CPS. It also enhances understanding of UDM security in CPS contexts. Practically, this study provides actionable strategies for implementing secure UDMs across sectors such as healthcare, smart cities, and governance, thereby improving data security and trust in CPS through practical mitigation measures. Policy-wise, the study informs data protection regulations and standards for CPS and UDMs and encourages the adoption of secure UDM practices in critical sectors.