Phishing detection in facial recognition using AACO enhanced GLCM features in machine learning
Srinithi. S
Phishing attacks exploiting facial recognition pose rising threats by mimicking legitimate biometric authentication. This study introduces a novel phishing detection framework using Artificial Aquarium Colony Optimization (AACO)-enhanced Gray Level Co-occurrence Matrix (GLCM) features combined with machine learning classifiers. AACO optimizes GLCM texture parameters for robust facial image analysis, capturing subtle phishing artifacts like synthetic distortions. Evaluated on custom and public datasets, the approach achieves 97.2% accuracy and outperforms standard GLCM-SVM by 12%, with low false positives in real-time scenarios. It offers a scalable solution for securing face-based systems.