Prevention of cybersecurity risks in contemporary communication systems depends on phishing email detection. This work presents an optimal deep learning method using the Hill Climbing (HC) algorithm for hyperparameter optimization and BERT for feature extraction to improve phishing detection. Using a Kaggle dataset, the model was trained with balanced precision, recall, and F1-scores for phishing and safe emails with a 95% accuracy. In terms of decreased loss and improved generalization, a comparative study encompassing GRU, LSTM, RNN, Logistic Regression, and SVM showed the suggested method’s excellence. The results highlight how well feature extraction combined with optimization methods could help to identify phishing emails in practical environments.
Optimized Deep Learning Based Phishing Email Detection Using BERT and Hill Climbing Algorithm
Castiglione, Arcangelo;
2025
Abstract
Prevention of cybersecurity risks in contemporary communication systems depends on phishing email detection. This work presents an optimal deep learning method using the Hill Climbing (HC) algorithm for hyperparameter optimization and BERT for feature extraction to improve phishing detection. Using a Kaggle dataset, the model was trained with balanced precision, recall, and F1-scores for phishing and safe emails with a 95% accuracy. In terms of decreased loss and improved generalization, a comparative study encompassing GRU, LSTM, RNN, Logistic Regression, and SVM showed the suggested method’s excellence. The results highlight how well feature extraction combined with optimization methods could help to identify phishing emails in practical environments.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
