StegaINR4MIH: steganography by implicit neural representation for multi-image hiding
This addresses the challenge of embedding multiple images without quality loss for applications in secure communication, though it appears incremental as it builds on implicit neural representations.
The paper tackles the problem of multi-image hiding in steganography, where embedding multiple secret images into a cover image often causes issues like contour shadowing or color distortion; the result is a novel framework that achieves PSNR values exceeding 42 for two images and 39 for five images, demonstrating high-quality recovery and undetectability.
Multi-image hiding, which embeds multiple secret images into a cover image and is able to recover these images with high quality, has gradually become a research hotspot in the field of image steganography. However, due to the need to embed a large amount of data in a limited cover image space, issues such as contour shadowing or color distortion often arise, posing significant challenges for multi-image hiding. In this paper, we propose StegaINR4MIH, a novel implicit neural representation steganography framework that enables the hiding of multiple images within a single implicit representation function. In contrast to traditional methods that use multiple encoders to achieve multi-image embedding, our approach leverages the redundancy of implicit representation function parameters and employs magnitude-based weight selection and secret weight substitution on pre-trained cover image functions to effectively hide and independently extract multiple secret images. We conduct experiments on images with a resolution of from three different datasets: CelebA-HQ, COCO, and DIV2K. When hiding two secret images, the PSNR values of both the secret images and the stego images exceed 42. When hiding five secret images, the PSNR values of both the secret images and the stego images exceed 39. Extensive experiments demonstrate the superior performance of the proposed method in terms of visual quality and undetectability.