BIG DATA ANALYTICS FOR CYBERSECURITY THREAT DETECTION: A REVIEW

Abstract

Modern digital ecosystems built on cloud platforms, the Internet of Things (IoT), and artificial intelligence have made cyberattacks both more frequent and more complex. Conventional security tools increasingly struggle to detect and respond to sophisticated intrusions as they unfold. Big Data Analytics (BDA) has emerged as a leading response to this gap, offering the capacity to process enormous volumes of structured and unstructured security data in order to surface hidden patterns, anomalies, and emerging threats. This review examines how the cybersecurity threat landscape has changed and how big data analytics contributes to stronger detection and response capabilities. It considers the defining traits of big data — volume, velocity, variety, veracity, and value — and surveys the technology stack commonly used to manage it, including Hadoop, Apache Spark, Kafka, Flink, Hive, HBase, and various NoSQL systems. The paper further examines how machine learning, when paired with big data infrastructure, enables real-time intrusion detection, anomaly identification, and predictive security analytics. Persistent obstacles are also discussed, among them advanced persistent threats, IoT-specific weaknesses, AI-enabled attacks, and cloud security gaps. The review closes by summarizing recent technical progress and arguing for scalable, intelligent, data-driven security architectures capable of safeguarding today's digital infrastructure against an evolving threat environment.