Feature-Based Coverless Information Hiding Using Vision Transformer

This study introduces an innovative coverless steganography method aimed at enhancing the security and efficiency of covert communication through digital images. The proposed method utilizes a pre-trained Vision Transformer (ViT) model to extract features and then divides the extracted features into non-overlapping blocks. The average coefficient for each feature block was calculated for hash sequence generation. Subsequently, a binary hash sequence is generated from the mean coefficients of feature blocks. Utilizing inverted indexing, the method dynamically manages hash sequences and their corresponding images and ensures the accurate extraction of confidential data. The results indicate that the proposed coverless information method significantly enhances the imperceptibility and security of hidden data compared to traditional approaches, rendering it a valuable technique for covert communication. The proposed method demonstrates exceptional performance in concealing confidential information within the images. It can embed up to 20 bits per image while maintaining near-perfect accuracy against numerous non-geometric attacks. For geometric attacks, such as rotation, the method achieved an accuracy of over 80%. Notably, it requires fewer images for data hiding than existing techniques, requiring only four images to conceal 10 bits of information, whereas other methods typically require 5–7 images. The robustness of this method was evaluated using ImageNet and Caltech-256 datasets. The results indicate 100% accuracy against various image processing attacks, including JPEG compression, filtering, and noise addition, highlighting its resilience and effectiveness in preserving hidden information.