🔐 Hybrid Crypto + Genetic Algorithm Platform

A Flask-based web application that implements hybrid cryptographic techniques optimized using Genetic Algorithms for both text and image encryption/decryption.

🌟 Features

🖼️ Image Encryption/Decryption

• Upload images in various formats (JPG, PNG, etc.)
• Encrypt images using GA-optimized keys
• Decrypt encrypted images to recover original content
• Download processed images
• Visual comparison of original, encrypted, and decrypted images

📝 Text Encryption/Decryption

• Encrypt text messages using Vigenère cipher with GA-optimized keys
• Decrypt encrypted text back to original plaintext
• Simple textarea-based interface

🧬 Genetic Algorithm Optimization

• Automatic key generation using Genetic Algorithm
• Population-based search for optimal encryption keys
• Fitness evaluation based on encryption quality
• Evolution over multiple generations for key improvement

📁 Project Structure

Hybrid_Crypto_GA/
│
├── app.py                    # Flask backend (main application)
├── encryption.py             # Encryption/decryption logic
├── genetic_algorithm.py      # GA optimization implementation
│
├── static/
│   ├── uploads/              # Temporary uploaded images
│   └── results/              # Encrypted/decrypted images
│
└── templates/
    └── index.html            # Frontend user interface

🚀 Getting Started

Prerequisites

Make sure you have Python 3.7+ installed on your system.

Installation

1. Clone the repository

git clone https://github.com/Jay121305/Hybrid-Image-Encryption-using-Genetic-Algorithm-.git
cd Hybrid_Crypto_GA

2. Install required dependencies

pip install flask pillow numpy

Running the Application

1. Start the Flask server

python app.py

2. Open your browser and navigate to

http://localhost:5000

3. The application will run the Genetic Algorithm optimization on startup (this may take a moment)

🎯 How It Works

Genetic Algorithm Process

1. Initialization: Random population of encryption keys is generated
2. Fitness Evaluation: Each key is evaluated based on encryption quality
3. Selection: Best-performing keys are selected for reproduction
4. Crossover: Selected keys are combined to create offspring
5. Mutation: Random modifications introduce diversity
6. Evolution: Process repeats for multiple generations
7. Convergence: Optimal keys are identified and used for encryption

The GA typically runs for 40-50 generations, continuously improving the encryption key quality.

Encryption Methods

• Image Encryption: Pixel-level manipulation using the GA-optimized image key
• Text Encryption: Vigenère cipher using the GA-optimized text key

📊 Results

Image Encryption Example

Encrypted Image:

Original image is transformed into encrypted noise pattern

Decrypted Image:

Encrypted image is successfully recovered to original form

Text Encryption Example

Encrypted Text: Plain text: "HELLOWORLD" → Encrypted: "WEDRDWGXAD"

Decrypted Text: Encrypted text is successfully decrypted back to: "HELLOWORLD"

🎨 User Interface

The platform features a modern, dark-themed interface with:

• Image Encryption/Decryption Section (Blue accent)

  • File upload with visual feedback
  • Encrypt/Decrypt dropdown selector
  • Result display with download option
  • Success/error notifications

• Text Encryption/Decryption Section (Purple accent)

  • Textarea for text input
  • Encrypt/Decrypt dropdown selector
  • Result display area
  • Success/error notifications

🔬 Technical Details

Genetic Algorithm Parameters

• Population Size: 20 individuals
• Generations: 40-50 iterations
• Mutation Rate: Configurable
• Selection Method: Tournament/Fitness-based
• Crossover: Single/Multi-point

Encryption Specifications

• Image Key: Generated by GA for pixel manipulation
• Text Key: Generated by GA for Vigenère cipher
• Key Space: Large enough to ensure security

📈 Performance

The GA optimization typically shows:

• Initial Best Fitness: 0.40-0.50
• Final Best Fitness: 0.95-0.99
• Average Fitness Improvement: Consistent increase over generations
• Convergence: Usually within 30-40 generations

Example GA output:

Running GA — this may take a bit...
Gen   0 | Best: 0.9700 | Avg: 0.3650
Gen   5 | Best: 0.9800 | Avg: 0.8680
Gen  10 | Best: 0.9900 | Avg: 0.7965
Gen  15 | Best: 0.9900 | Avg: 0.9325
...
Gen  40 | Best: 0.9900 | Avg: 0.8990

🛡️ Security Considerations

• Keys are generated using genetic algorithm optimization
• Image encryption uses pixel-level manipulation
• Text encryption uses Vigenère cipher (educational purposes)
• Note: This is an educational project. For production use, consider implementing AES, RSA, or other industry-standard algorithms.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

📝 Future Enhancements

• Add more encryption algorithms (AES, RSA)
• Implement encryption strength metrics
• Add batch processing for multiple images
• Visualize GA evolution process with graphs
• Export encryption keys securely
• Add password-based key derivation
• Support for more file formats (PDF, DOCX)

👨‍💻 Author

Jay Gautam - @Jay121305

📄 License

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

🙏 Acknowledgments

• Genetic Algorithm concepts and implementation
• Flask framework for web development
• Pillow library for image processing
• Cryptographic principles and hybrid encryption techniques

📧 Contact

For questions or feedback, please open an issue on GitHub or contact the repository owner.

---

⭐ Star this repository if you found it helpful!

🔐 Made with ❤️ using Python, Flask, and Genetic Algorithms