StegaINR4MIH: steganography by implicit neural representation for multi-image hiding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dong, Weina, Liu, Jia, Chen, Lifeng, Sun, Wenquan, Pan, Xiaozhong, Ke, Yan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929540889051136
author Dong, Weina
Liu, Jia
Chen, Lifeng
Sun, Wenquan
Pan, Xiaozhong
Ke, Yan
author_facet Dong, Weina
Liu, Jia
Chen, Lifeng
Sun, Wenquan
Pan, Xiaozhong
Ke, Yan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10117
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle StegaINR4MIH: steganography by implicit neural representation for multi-image hiding
Dong, Weina
Liu, Jia
Chen, Lifeng
Sun, Wenquan
Pan, Xiaozhong
Ke, Yan
Computer Vision and Pattern Recognition
Cryptography and Security
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.
title StegaINR4MIH: steganography by implicit neural representation for multi-image hiding
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2410.10117