Journal of AI, Data Science and Cyber Systems

Data-Centric Cyber Intelligence and Threat Analytics focuses on collecting, integrating, and analyzing large volumes of data, from diverse sources, of high quality and value. It enables organizations to understand, identify, forecast, and mitigate cyber threats. Instead of employing isolated security tools or signatures, this paradigm invests heavily in data (which is treated as the most important asset available to an organization, a measure of its value and worth) and combines diverse elements (network data, logs, systems, endpoints, user cloud services, behavior, and external threat intelligence). Data is processed through various advanced techniques and AI. The aim is to determine and explain the disparate factors and data sets in a malicious manner, as well as identify and explain the hostile phenomena, evolving attack strategies, and weaknesses in systems. Data centric cyber intelligence enables proactive and adaptive defense, focusing on quality, context and fusion of data. Threats, adversaries, and timely infrastructure can be analyzed for risk via machine learning models and graph-based analytics. This approach supports predictive threat modelling, as historical and real-time data are used to anticipate the intent of an attacker and the most likely paths for an attack. Strong data pipelines, governance, and explainable analytics guarantee framework, actionable, and insightful analytics. Threat analytics and data centric cyber intelligence are especially important in environments like enterprise networks, critical infrastructure, and national cyber defense systems. These are high-volume and complex systems that need timely insight for effective security operations.