Real-Time Phishing Detection and User Education Using Machine Learning
Authors/Creators
-
1.
Lewis University
Description
Phishing emails trick users into giving away sensitive information by pretending to be from trusted sources. This paper
introduces a real-time phishing detection system that also teaches users how to spot phishing attempts. The system uses natural language processing (NLP) techniques such as sentiment analysis and TF-IDF vectorization and a Random Forest classifier to accurately identify phishing emails. When a suspicious email is detected, the system immediately alerts the user through a graphical interface and provides helpful safety tips. We explain how the dataset was collected, processed, and used to train the model. Results show that the system effectively separates phishing emails from legitimate ones. By combining real-time detection with user education, our approach helps reduce the chances of phishing attacks and increases user awareness.
Files
Real_Time_email_phishing_detection (1).pdf
Files
(343.1 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:10dbdfed67aa5a147ab14fa6041d85b5
|
343.1 kB | Preview Download |
Additional details
Software
- Repository URL
- https://huggingface.co/spaces/HudaHajira/Detect_Email_Phishing
- Programming language
- Python
- Development Status
- Active
References
- S. A. Salloum, M. Al-Emran, and K. Shaalan (2022) presented a systematic literature review on phishing email detection using NLP techniques [DOI: 10.1109/ACCESS.2022.3166740].
- H. Tusher, M. S. Rahman, and M. N. I. Uddin (2024) conducted a comprehensive review on email spam detection methods and challenges [DOI: 10.1109/ACCESS.2024.3467996].
- S. Kumar, H. Saini, and S. Mehta (2020) explored machine learning algorithms for email spam detection at the 2020 International Conference on Emerging Trends in Information Technology and Engineering.
- H. Thakur and S. Arora (2022) compared machine learning algorithms for email spam detection at the IEEE 12th International Conference on Cloud Computing, Data Science & Engineering (Confluence).
- D. Hyelhirra et al. (2023) performed a comparative analysis of machine learning algorithms for spam detection in the International Journal of Advanced Computer Science and Applications [Available: https://www.researchgate.net/publication/381957816].
- C. Paradkar et al. (2023) examined phishing email detection using machine learning and deep learning at the IEEE Pune Section International Conference (PuneCon).
- B. Gogoi and F. Ahmed (2022) proposed a transfer learning approach using pretrained transformers for phishing detection at the International Conference on Intelligent Engineering and Management (ICIEM).
- J. Heiding et al. (2024) discussed phishing email generation and detection using large language models in IEEE Transactions on Dependable and Secure Computing.
- T. Schafer, R. Luh, and S. Mahlke (2015) studied compromised email account detection based on metadata access patterns at the IEEE 14th International Symposium on Network Computing and Applications.
- H. Sultana (2025) created a Hugging Face Space for email phishing detection [Available: https://huggingface.co/spaces/HudaHajira/Detect-Email-Phishing].