Developing a sophisticated stacking ensemble classifier for accurate phishing website detection.
A hybrid deep learning model combining Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) achieves high accuracy in detecting phishing websites.
A novel hybrid learning paradigm that combines federated learning and continual learning, enabling distributed nodes to continually update models on streams of new phishing data without accumulating data, while leveraging an attention-based classifier model tailored for web phishing detection.