Email spam detection using machine learning

This paper introduced a machine learning- based email fraud detection methodology using text processing and metadata analysis. Proposed system has good classification accuracy    and    robust    detection.   Deep learning-based transformer models for contextual understanding, federated learning for privacy-preserving collaboration across organisations, real-time URL threat intelligence feeds, and adversarially robust training strategies are future goals.

[1]Chen et al., “Machine Learning-Based Phishing Email Detection Using Textual and Structural  Features,”  IEEE  Access,  2023. [2]M. Kumar et al., “Hybrid Email Fraud Detection Using NLP and Metadata Analysis,” IEEE   Transactions   on   AI,   2024.  [3]Lin Zhang et al., “Contextual Embedding Models for Phishing Detection,” IEEE Transactions on Information Forensics and Security,      2024.   [4]Patel et al., “Ensemble Learning for Cybersecurity Email Classification,” IEEE Access,   2025.   [5]H.Lee et al., “Scalable Machine Learning Models for Enterprise Email Security,” IEEE Internet   of   Things   Journal,   2025. [6]A. Singh et al., “Explainable AI Techniques for Cyber Threat Detection,” IEEE Transactions on Neural Networks and Learning Systems,           2026.   [7]T.Nguyen et al., “Robust Fraud Detection Systems Using Supervised Learning,” IEEE Access,       2023. [8]P.Wang et al., “Advanced Feature Engineering for Phishing Email Classification,” IEEE Transactions on AI, 2024.   [9]K.Roy et al., “RealTime Email Threat Detection Using Optimised Classifiers,” IEEE Access,           2025.   [10]J.Brown et al., “Adaptive Cybersecurity Systems Using Machine Learning,” IEEE Access,    2026.