Transparent and Trustworthy CyberSecurity: An XAI-Integrated Big Data Framework for Phishing Attack Detection

Muhammad Nauman¹Hafiz Muhammad Usman Akhtar¹Huseyn Gorbani²Muhammad Hadi Ul Hassan³Muhammad A B Fayyaz^4*Raheel Nawaz⁵

• ¹The Islamia University of Bahawalpur Pakistan, Bahawalpur, Pakistan
• ²Queen Mary University of London, London, United Kingdom
• ³University of Bolton, Bolton, United Kingdom
• ⁴Manchester Metropolitan University, Manchester, United Kingdom
• ⁵University of Staffordshire, Stoke-on-Trent, United Kingdom

The exponential growth of heterogeneous, high-velocity CyberSecurity data generated by modern digital infrastructures presents both opportunities and challenges for threat detection, particularly in the face of increasingly sophisticated cyber-attacks. Traditional security tools struggle to process such data effectively, necessitating scalable Big Data Analytics and advanced Machine Learning (ML) techniques. However, the opaque, black box nature of many ML models limits interpretability, trust, and regulatory compliance in high-stakes environments. This study proposes an integrated framework combining Big Data technologies, ML, and Explainable Artificial Intelligence (XAI) to enable accurate, transparent, and real-time phishing attack detection. Leveraging distributed computing and stream processing, the framework efficiently handles large, diverse datasets, while XAI techniques provide human-understandable explanations of model decisions. Experimental evaluation on four publicly available CyberSecurity datasets demonstrates improved detection performance and interpretability, offering actionable insights into malicious URL patterns. The proposed approach advances interpretable, scalable, and trustworthy CyberSecurity analytics, bridging the gap between predictive accuracy and decision transparency.