AegisAI - AI-Powered Phishing Detection System

A comprehensive cybersecurity solution that uses machine learning to detect phishing websites and protect users from cyber threats.

🚀 Features

• URL Analysis: Advanced feature extraction and ML-based phishing detection
• Image Analysis: Screenshot analysis for phishing detection
• User Authentication: Secure login/registration with bcrypt password hashing
• Scan History: Comprehensive tracking and analytics
• Real-time Dashboard: Interactive charts and statistics
• Security Settings: 2FA, session management, and monitoring
• Modern UI: Clean, minimal design with smooth animations

📁 Project Structure

AegisAI/
├── app.py                 # Main Flask application
├── models.py              # Database models (User, ScanHistory, LoginActivity)
├── routes.py              # API routes and endpoints
├── config.py              # Configuration settings
├── train_model.py         # ML model training script
├── requirements.txt       # Python dependencies
├── utils/
│   ├── __init__.py
│   └── feature_extractor.py  # URL feature extraction
├── uploads/               # Image upload directory
├── templates/             # HTML templates
│   ├── index.html
│   ├── login.html
│   ├── dashboard.html
│   ├── history.html
│   └── settings.html
└── aegis_model.pkl        # Trained ML model

🛠️ Installation

1. Clone the repository

git clone <repository-url>
cd AegisAI

2. Create virtual environment

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies

pip install -r requirements.txt

4. Train the ML model

python train_model.py

5. Run the application

python app.py

The application will be available at http://localhost:5000

📡 API Endpoints

Authentication

• POST /register - User registration
• POST /login - User login
• POST /logout - User logout
• PUT /update-profile - Update user profile

Analysis

• POST /analyze-url - Analyze URL for phishing
• POST /analyze-image - Analyze image for phishing

Data

• GET /history - Get scan history
• GET /dashboard-stats - Get dashboard statistics
• GET /login-activity - Get login activity

🔧 Configuration

Environment Variables

SECRET_KEY=your-secret-key
DATABASE_URL=sqlite:///aegisai.db
FLASK_ENV=development

Database Setup

The application uses SQLite by default. The database is automatically created on first run.

Model Training

The Random Forest model is trained on URL features including:

• URL length and structure
• Domain characteristics
• Suspicious word detection
• IP address detection
• Brand impersonation
• TLD analysis

🎯 ML Model Features

URL Feature Extraction

• Basic Features: URL length, domain length, path length
• Domain Features: Subdomains, special characters, TLD analysis
• Security Features: IP addresses, hex encoding, suspicious words
• Brand Protection: Known brand impersonation detection
• Risk Scoring: Comprehensive risk assessment (0-100)

Model Performance

• Algorithm: Random Forest Classifier
• Accuracy: ~95% on test data
• Features: 30+ extracted features
• Output: Prediction, confidence score, risk score

🔒 Security Features

• Password Hashing: bcrypt for secure password storage
• Session Management: Secure session handling
• Login Monitoring: Track login attempts and IP addresses
• Input Validation: Comprehensive input sanitization
• File Upload Security: Safe file handling with type validation

📊 Analytics & Monitoring

• Real-time Statistics: Total scans, phishing detection rates
• Trend Analysis: Weekly detection patterns
• User Activity: Login tracking and session management
• Performance Metrics: Processing time and accuracy

🎨 Frontend Features

• Modern Design: Black and white theme with Belleza font
• Responsive Layout: Mobile-friendly design
• Interactive Charts: Real-time data visualization
• Smooth Animations: Professional user experience
• Drag & Drop: File upload functionality

🚀 Deployment

Production Setup

1. Set environment variables
2. Configure production database
3. Enable HTTPS
4. Set up reverse proxy (nginx)
5. Configure SSL certificates

Docker Deployment

FROM python:3.9-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 5000
CMD ["python", "app.py"]

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Support

For support and questions:

• Create an issue in the repository
• Check the documentation
• Review the API endpoints

🔮 Future Features

• Email notifications for high-risk detections
• Advanced image analysis with CNN
• Real-time URL scanning
• Browser extension integration
• API rate limiting
• Multi-language support
• Advanced threat intelligence

---

AegisAI - Protecting users from cyber threats with AI-powered security.