In-context learning for the classification of manipulation techniques in phishing emails
Résumé
Traditional phishing detection often overlooks psychological manipulation. This study investigates using Large Language Model (LLM) In-Context Learning (ICL) for fine-grained classification of phishing emails based on a taxonomy of 40 manipulation techniques. Using few-shot examples with GPT-4o-mini on real-world French phishing emails, we evaluated performance against a human-annotated test set. The approach effectively identifies prevalent techniques (e.g., Baiting, Curiosity Appeal, Request For Minor Favor) with a promising accuracy of 0.76 significantly outperforming traditional machine learning methods including KNN (0.65), Random Forest (0.65), SVM (0.65), Logistic Regression (0.63), and fine-tuned BERT (0.62).
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |