Phishing Detection in Customer Support E-mails

Phishing is the most widespread cyberattack in the world, and email remains the most frequently used medium. Traditional machine learning models are one method for phishing detection. Many studies have been conducted to identify phishing in customer service emails. However, no one has looked into combining the Transformer and Graph Neural Network (GNN) to identify fraudulent emails sent to customer service. This study proposes a hybrid model that combines the GNN for graphical features with the RoBERTa for textual features. The experiments were performed with the CEAS-08 phishing email dataset, an openly available benchmark released in the 2008 CEAS Live Spam Challenge. The dataset is partitioned into 70% for training, 30% for validation, and testing to evaluate performance. The Hybrid RoBERTa + GNN model developed here attained an astonishing accuracy of 98.40% with the frozen RoBERTa base on Google Colab Free. In comparison with other traditional classifiers like SVM, KNN, and Naive Bayes, the new hybrid model provides more contextualized knowledge with RoBERTa and relation knowledge with GNN. Future work may investigate fine-tuning the RoBERTa base to further improve its performance. While the main objective is to open a new research pathway that offers deep contextual and structural insights, the suggested model achieves this aim, unlike conventional models that fall short in this regard.