This project integrates EfficientNet B6 and Vision Transformer (ViT) for advanced image steganalysis. Aimed at detecting hidden information within digital images, our approach leverages the strengths of both architectures to improve detection accuracy and efficiency.

Install dependencies: ./setup.sh

To train the model: python train_models.py --model efficientnet-b6 --batch_size 32 --checkpoint_dir checkpoints/

• Integration of EfficientNet B6 and ViT for robust steganalysis
• Comprehensive performance evaluation metrics
• Detailed quantitative and qualitative analysis with weights and biases

Contributions are welcome! Please fork the repository and submit pull requests with your enhancements.

Vignesh Sivakumar - [[email protected]] - [https://github.com/knoxrm]