Paper Title
Detection of Phishing Websites Using Hybrid Approach

Abstract
Phishing attacks remain a major threat to cybersecurity because they use fraudulent websites to fool users into divulging personal information. Our method proposes a hybrid approach that combines encoder representations from pre-trained transformers (BERT, RoBERTa and Electra) with artificial neural networks (ANN) for accurate phishing website identification. BERT and other state-of-the-art natural language processing methods are used to extract contextual embeddings from URLs. These embeddings are then used to train a specially designed artificial neural network (ANN) classifier, which learns to distinguish between legitimate and phishing websites. Keywords - Transformer Embeddings, Phishing Detection, ANN,Feature Extraction,URL.