https://github.com/subbareddy2004/fie-balu-phishing-detection
https://github.com/subbareddy2004/fie-balu-phishing-detection
Last synced: over 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/subbareddy2004/fie-balu-phishing-detection
- Owner: Subbareddy2004
- Created: 2025-03-30T18:11:50.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-30T18:13:13.000Z (over 1 year ago)
- Last Synced: 2025-03-30T19:24:09.324Z (over 1 year ago)
- Language: Python
- Size: 309 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
🚨 AI-powered phishing detection system 🚨
## ⚙️ About the Project
An AI-powered phishing detection system using machine learning to classify emails as **phishing** or **safe**. Built using **Python**, **Streamlit**, and **scikit-learn**, this system analyzes email bodies and URLs to detect phishing attempts.
[](https://ai-powered-phishing-detection-system-ples7i6bq2tzkaguiykzzt.streamlit.app/)
## 🚀 Features
- **Email Body Analysis**: Uses text processing to identify phishing patterns.
- **URL Scanning**: Extracts and evaluates URLs within the email to detect malicious links.
- **Machine Learning**: Trained with labeled phishing data to make predictions on email content.
- **Interactive UI**: Built with Streamlit for real-time predictions.
## 🧑💻 Technologies Used
- **Python** 🐍
- **Streamlit** 🌐
- **scikit-learn** 🤖
- **pandas** 📊
- **nltk** 🧠
- **Requests** 🌍
- **BeautifulSoup** 🍲
## 🎯 Installation & Setup
1. Clone the repository
```bash
git clone https://github.com/yourusername/AI-Powered-Phishing-Detection-System.git
cd AI-Powered-Phishing-Detection-System
2. Install Dependencies
Create and activate a virtual environment, then install required packages:
```bash
python -m venv venv
source venv/bin/activate # For macOS/Linux
venv\Scripts\activate # For Windows
pip install -r requirements.txt
3. Run the App
Start the Streamlit app to launch the phishing detection system:
```bash
streamlit run phishing_detection.py
4. Upload Dataset for Training (Optional)
Upload a CSV file with columns email_body (content of the email) and label (1 for phishing, 0 for safe) to train the model.
🔍 How to Use
- **Training the Model**: Upload a CSV file containing emails labeled as phishing or safe.
- **Prediction**: Enter the body of an email, and the system will classify it as phishing or safe.
Example Email to Test:
- **Phishing Email**:
```bash
Congratulations! You've won a $1000 gift card. Click here to claim your prize: http://phishing.com
- **Safe Email**:
```bash
Hey, just checking in on our project. Let me know your availability for a meeting.
5. Check Prediction
Click Check Phishing to see the prediction results for the email you entered.
## 📊 Results
The system will display whether the email is a phishing attempt or safe based on its body content and URL features.
## 🛠️ Contributing
Contributions are welcome! If you'd like to improve the system or add new features, feel free to fork the repository and submit a pull request.
## 🙌 Acknowledgements
- Streamlit for creating the amazing interface.
- scikit-learn for machine learning tools.
- Shields.io for badges.
- FontAwesome for awesome icons.
## 💻 Preview
## Phishing Email:
## Safe Email:
## 🌐 Connect with Me
- 📧 [Email](mailto:gauravghandat12@gmail.com)
- 💼 [LinkedIn](www.linkedin.com/in/gaurav-ghandat-68a5a22b4)
# FIE-Balu-Phishing-detection