Image hiding aims to conceal one or more secret images within a cover image of the same resolution. Due to strict capacity requirements, image hiding is commonly called large-capacity steganography. In this paper, we propose StegFormer, a novel autoencoder-based image-hiding model. StegFormer can conceal one or multiple secret images within a cover image of the same resolution while preserving the high visual quality of the stego image. In addition, to mitigate the limitations of current steganographic models in real-world scenarios, we propose a normalizing training strategy and a restrict loss to improve the reliability of the steganographic models under realistic conditions. Furthermore, we propose an efficient steganographic capacity expansion method to increase the capacity of steganography and enhance the efficiency of secret communication. Through this approach, we can increase the relative payload of StegFormer to 96 bits per pixel without any training strategy modifications. Experiments demonstrate that our StegFormer outperforms existing state-of-the-art (SOTA) models. In the case of single-image steganography, there is an improvement of more than 3 dB and 5 dB in PSNR for secret/recovery image pairs and cover/stego image pairs.
We use normalizing training strategy and a restrict loss to enhance the reliability of the steganographic models in real-world scenarios. The figure bellow shows the quality of the recovery image in real-world scenarios is significantly improved and the performance of StegFormer is still the best.
We use StegExpose to measure StegFormer's anti-steganalysis ability. The Figure bellow shows the receiver operating characteristic (ROC) curve of StegFormer. We can see that the stego images generated by StegFormer have high security and can fool the StegExpose.
