Deep Learning Approaches for Multi-Class Classification of Phishing Text Messages

Phishing attacks, particularly Smishing (SMS phishing), have become a major cybersecurity threat, with attackers using social engineering tactics to take advantage of human vulnerabilities. Traditional detection models often struggle to keep up with the evolving sophistication of these attacks, especially on devices with constrained computational resources. This research introduces a chain transformer model that integrates GPT-2 for synthetic data generation and BERT for embeddings to detect Smishing within a multiclass dataset, including minority smishing variants. By utilizing small, open-source models optimized for resource-limited environments, this approach improves both accuracy and efficiency in detecting a variety of phishing threats. Experimental results demonstrate a precision rate exceeding 97% in detecting phishing attacks across multiple categories, showcasing the model’s potential for deployment on resource-constrained devices.