A Robust and Explainable Transformer-Based Framework for Phishing Email Detection
Researchers have developed a new framework using DistilBERT, a lightweight Transformer model, to enhance the detection of sophisticated phishing emails. This framework incorporates adversarial training techniques to improve its resilience against noise and perturbations, making it more robust than standard models. Additionally, it integrates Explainable AI (XAI) methods like LIME, SHAP, and Integrated Gradients to provide transparent interpretations of its decision-making process, aiming to build user trust. AI
IMPACT Enhances cybersecurity by providing more robust and transparent AI-driven phishing detection.