Big Data-Based Intelligent Intrusion Detection System for Computer Network Security

Abstract

The rapid growth of computer networks, cloud computing, Internet services, and digital communication has resulted in an unprecedented increase in the volume, velocity, and variety of network traffic. While these technological advancements have significantly improved connectivity and information sharing, they have also expanded the attack surface for cybercriminals, leading to increasingly sophisticated cyber threats such as distributed denial-of-service (DDoS) attacks, malware propagation, botnets, phishing, insider threats, zero-day exploits, and advanced persistent threats (APTs). Traditional intrusion detection systems (IDSs), primarily based on signature matching and predefined attack patterns, have demonstrated limitations in detecting unknown attacks and processing the massive volume of security events generated by modern network infrastructures. Consequently, integrating Big Data technologies with intelligent intrusion detection has emerged as a promising solution for enhancing cybersecurity through scalable data processing, real-time threat analysis, and intelligent anomaly detection. This study proposes a Big Data-Based Intelligent Intrusion Detection System (BDI-IDS) for computer network security that integrates distributed data collection, big data preprocessing, feature extraction, machine learning-based intrusion detection, anomaly analysis, and intelligent decision support into a unified security framework. The proposed framework leverages distributed computing environments for processing large-scale network traffic while employing intelligent classification techniques to identify malicious activities with high detection accuracy and low false alarm rates.