Novel Interpretable and Robust Web-based AI Platform for Phishing Email Detection
About
Phishing emails continue to pose a significant threat, causing financial losses and security breaches. This study addresses limitations in existing research, such as reliance on proprietary datasets and lack of real-world application, by proposing a high-performance machine learning model for email classification. Utilizing a comprehensive and largest available public dataset, the model achieves a f1 score of 0.99 and is designed for deployment within relevant applications. Additionally, Explainable AI (XAI) is integrated to enhance user trust. This research offers a practical and highly accurate solution, contributing to the fight against phishing by empowering users with a real-time web-based application for phishing email detection.
Abdulla Al-Subaiey, Mohammed Al-Thani, Naser Abdullah Alam, Kaniz Fatema Antora, Amith Khandakar, SM Ashfaq Uz Zaman• 2024
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Spam Detection | Spam Base and Spam Filter Data Kaggle | -- | 2 | |
| Spam Detection | CLAIR collection of fraud email | -- | 1 | |
| Spam Detection | Enron 3100 spam 3100 ham | -- | 1 | |
| Spam Detection | SpamAssassin, Enron, Nazario (SA-JN and En-JN) | -- | 1 | |
| Spam Detection | Ling, Enron, PUA, SpamAssassin | -- | 1 | |
| Spam Detection | Enron 17171 spam, 16545 ham | -- | 1 | |
| Spam Detection | SpamAssassin Nazario 3-class | -- | 1 | |
| Spam Detection | SpamAssassin 1000 spam 5051 ham | -- | 1 |
Showing 8 of 8 rows