{"id":28919277,"url":"https://github.com/otuemre/emailphishingdetection","last_synced_at":"2026-04-13T18:01:51.852Z","repository":{"id":295704626,"uuid":"990971564","full_name":"otuemre/EmailPhishingDetection","owner":"otuemre","description":"A real-time phishing email detection system using Machine Learning (SVM, Logistic Regression, Naive Bayes) with FastAPI backend and custom domain deployment.","archived":false,"fork":false,"pushed_at":"2025-06-06T22:26:54.000Z","size":14453,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-13T18:43:03.145Z","etag":null,"topics":["cybersecurity","fastapi","huggingface","machine-learning","nlp","real-time","scikit-learn","spam-detection","svm-classifier","tfidf-vectorizer"],"latest_commit_sha":null,"homepage":"https://phishingdetection.net/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/otuemre.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-26T23:51:38.000Z","updated_at":"2025-06-06T22:26:58.000Z","dependencies_parsed_at":"2025-05-27T00:41:55.468Z","dependency_job_id":null,"html_url":"https://github.com/otuemre/EmailPhishingDetection","commit_stats":null,"previous_names":["otuemre/emailphishingdetection"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/otuemre/EmailPhishingDetection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/otuemre%2FEmailPhishingDetection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/otuemre%2FEmailPhishingDetection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/otuemre%2FEmailPhishingDetection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/otuemre%2FEmailPhishingDetection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/otuemre","download_url":"https://codeload.github.com/otuemre/EmailPhishingDetection/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/otuemre%2FEmailPhishingDetection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31764317,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T15:25:13.801Z","status":"ssl_error","status_checked_at":"2026-04-13T15:25:09.162Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cybersecurity","fastapi","huggingface","machine-learning","nlp","real-time","scikit-learn","spam-detection","svm-classifier","tfidf-vectorizer"],"created_at":"2025-06-22T03:05:26.193Z","updated_at":"2026-04-13T18:01:51.847Z","avatar_url":"https://github.com/otuemre.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 📧 Email Phishing Detection\n\n[![License: MIT](https://img.shields.io/github/license/otuemre/EmailPhishingDetection?style=flat-square)](./LICENSE.md)\n[![Deploy on Render](https://img.shields.io/badge/Deploy-Render-5e60ce?logo=render\u0026style=flat-square)](https://phishingdetection.net)\n[![Hugging Face Models](https://img.shields.io/badge/HuggingFace-SVM%20%7C%20TFIDF-orange?logo=huggingface\u0026style=flat-square)](https://huggingface.co/emreotu)\n\nDetect phishing emails in real-time using machine learning — trained on six merged datasets and deployed via a full-stack FastAPI app.\n\n🔗 **Live Demo**: [https://phishingdetection.net](https://phishingdetection.net)\n\n## 📚 Table of Contents\n\n- [What It Does](#-what-it-does)\n- [Tech Stack](#️-tech-stack)\n- [ML Models](#-ml-models)\n- [Sample Input](#-sample-input)\n- [Future Improvements](#-future-improvements)\n- [Project Structure](#-project-structure)\n- [Acknowledgements](#-acknowledgements)\n- [Author](#-author)\n\n---\n\n## 🧠 What It Does\n\nThis project allows users to paste real email content (sender, subject, body, etc.) and choose between three machine learning models to detect whether it's **Phishing** or **Legitimate**.\n\nIt combines:\n- 📊 Natural Language Processing (TF-IDF + NLTK)\n- 🤖 ML models (Naive Bayes, Logistic Regression, SVM)\n- 🌍 Live API deployment + responsive UI\n\n---\n\n## 🛠️ Tech Stack\n\n| Layer          | Tech                       |\n|----------------|----------------------------|\n| Frontend       | HTML, CSS, JavaScript      |\n| Backend        | FastAPI, Uvicorn           |\n| ML/NLP         | Scikit-learn, NLTK, joblib |\n| Deployment     | Render, Namecheap          |\n| Hosting Models | Hugging Face 🤗            |\n\n---\n\n## 🤖 ML Models\n\nChoose between:\n- ✅ Support Vector Machine (Best Accuracy)\n- ✅ Logistic Regression\n- ✅ Multinomial Naive Bayes\n\n### 📦 Hugging Face Models\n\n- 🔗 [SVM Model](https://huggingface.co/otuemre/email-phishing-svm)\n- 🔗 [TF-IDF Vectorizer](https://huggingface.co/otuemre/email-phishing-vectorizer)\n\n---\n\n## 🧪 Sample Input\n\n```\nSender: freeiphone@gmail.com\nSubject: Don't miss this chance!\nBody: Click the link to claim your free iPhone 14 Pro Max.\nDate: May 5, 2025\nModel: SVM\n```\n\n✔️ Output: **Phishing**\n\n---\n\n### 🚀 Future Improvements\n\n- **📡 Public API \u0026 Documentation**  \n  Provide a proper REST API endpoint with OpenAPI/Swagger documentation so developers can integrate the phishing detection system into their own applications.\n\n- **🎨 Improve the UI**  \n  Rebuild the frontend using a modern framework like React (possibly with Tailwind or Material UI) to create a more interactive and responsive user experience.\n\n- **🔗 URL-Based Model**  \n  Train and integrate a secondary model focused specifically on analyzing URLs for phishing characteristics such as domain structure, length, obfuscation, and suspicious keywords.\n\n- **📈 Expand the Dataset**  \n  Enhance the model's performance by collecting a larger and more diverse dataset of phishing and legitimate emails, improving generalization and reducing bias.\n\n- **🧠 Improve Model Explainability**  \n  Integrate explainable AI tools like SHAP or LIME to provide transparency into why the model classified an email as phishing or legitimate.\n\n- **📬 Real-Time Email API Integration (Optional)**  \n  Integrate with email providers like Gmail or Microsoft Outlook via API to allow live scanning of user inboxes (with permission) and flag suspicious messages in real time.\n\n---\n\n## 🗂️ Project Structure\n\n```\nEmailPhishingDetection/\n├── api/\n│   ├── main.py\n│   └── pipeline.py\n├── data/\n│   └── phishing_email.csv\n├── frontend/\n│   └── static/\n│       └── index.html\n├── models/\n│   ├── logistic_regression_model.joblib\n│   ├── naive_bayes_model.joblib\n│   ├── svm_model.joblib\n│   └── tfidf_vectorizer.joblib\n├── notebooks/\n│   └── 01_training.ipynb\n├── images/\n├── .gitignore\n├── LICENSE.md\n├── README.md\n├── render.yml\n└── requirements.txt\n```\n\n---\n\n## 🙏 Acknowledgements\n\nThis project uses the **Phishing Email Dataset** by [Naser Abdullah Alam on Kaggle](https://www.kaggle.com/datasets/naserabdullahalam/phishing-email-dataset).\n\nPlease cite the following article if using this dataset:\n\n\u003e **Al-Subaiey, A., Al-Thani, M., Alam, N. A., Antora, K. F., Khandakar, A., \u0026 Zaman, S. A. U. (2024, May 19).**  \n\u003e *Novel Interpretable and Robust Web-based AI Platform for Phishing Email Detection*.  \n\u003e ArXiv: [https://arxiv.org/abs/2405.11619](https://arxiv.org/abs/2405.11619)\n\n---\n\n## 👨‍💻 Author\n\n**Emre OTU**  \n🔗 [GitHub](https://github.com/otuemre) | [LinkedIn](https://linkedin.com/in/emreotu)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fotuemre%2Femailphishingdetection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fotuemre%2Femailphishingdetection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fotuemre%2Femailphishingdetection/lists"}