<![CDATA[Phishing remains a major cybersecurity threat because attacks increasingly combine fraudulent websites with deceptive email content. Existing detection models often focus on a single domain, such as URLs or emails, which limits their ability to capture heterogeneous phishing patterns. This study proposes a GA-optimized stacking ensemble framework for unified phishing website and email detection using multi-domain features. The framework combines URL structural attributes, email metadata, and semantic content features, while a Genetic Algorithm is used to reduce feature redundancy and select the most informative attributes. The proposed model is evaluated against baseline Random Forest, Gradient Boosting, and conventional Stacking classifiers using Accuracy, F1-score, AUC-ROC, cross-validation stability, robustness under noise, and inference latency. Experimental results show that the proposed GA-Stacking model achieves 98.1% accuracy, 97.6% F1-score, and 0.947 AUC-ROC, outperforming Random Forest, Gradient Boosting, and standard Stacking models. The model also reduces the feature set from 72 to 31 features and maintains strong robustness under simulated noise, with F1-score remaining at 92.0% under 30% perturbation. These findings indicate that evolutionary feature optimization improves the stability, efficiency, and robustness of stacking ensemble learning for multi-domain phishing detection.]]>
Copyrights © 2026
