Transparent and trustworthy CyberSecurity: an XAI-integrated big data framework for phishing attack detection

The exponential growth of heterogeneous, high-velocity CyberSecurity data generated by modern digital infrastructures presents both opportunities and challenges for threat detection, especially against increasingly sophisticated cyber-attacks. Traditional security tools struggle to process such data effectively, highlighting the need for scalable Big Data Analytics and advanced Machine Learning (ML) techniques. However, the black-box nature of many ML models limits interpretability, trust, and regulatory compliance in high-stakes environments.

This study proposes an integrated framework that combines Big Data technologies, ML models, and Explainable Artificial Intelligence (XAI) to enable accurate, transparent, and real-time phishing attack detection. The framework leverages distributed computing and stream processing for efficient handling of large and diverse datasets while incorporating XAI methods to generate human-understandable model explanations.

Experimental evaluation conducted on four publicly available CyberSecurity datasets demonstrates improved phishing detection performance, enhanced interpretability of model decisions, and actionable insights into malicious URL behavior and patterns.

The proposed approach advances interpretable and scalable CyberSecurity analytics by addressing the gap between predictive accuracy and decision transparency. By integrating Big Data processing with XAI-driven ML, the framework offers a trustworthy solution for real-time threat detection, supporting informed decision-making and regulatory compliance.