Effective Message Hiding with Order-Preserving Mechanisms


Gao Yu (University of Queensland), Xuchong QIU (Bosch), Zihan Ye (Xi'an Jiaotong-Liverpool University)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Message hiding, a technique that conceals secret message bits within a cover image, aims to achieve an optimal balance among message capacity, recovery accuracy, and imperceptibility. While convolutional neural networks (CNNs) have notably improved message capacity and imperceptibility, obtaining high recovery accuracy remains challenging. This arises because, in contrast to image data, the sequential arrangement of message bits is imperative, but convolutional operations encounter inherent difficulties in preserving this critical order. In addition, CNNs also struggle to effectively address the large discrepancy between these two uncorrelated modalities. To address this, we propose StegaFormer, an innovative MLP-based framework designed to preserve bit order and enable global fusion between modalities. Specifically, StegaFormer incorporates three crucial components: Order-Preserving Message Encoder (OPME), Order-Preserving Message Decoder (OPMD), and Global Message-Image Fusion (GMIF). OPME and OPMD aim to preserve the order of message bits by segmenting the entire sequence into equal-length segments and incorporating sequential information during encoding and decoding. Meanwhile, GMIF employs a cross-modality fusion mechanism to effectively fuse the features from the two uncorrelated modalities. Experimental results on the COCO and DIV2K datasets demonstrate that StegaFormer significantly outperforms existing state-of-the-art methods in terms of recovery accuracy, message capacity, and imperceptibility. We will make our code publicly available.

Citation

@inproceedings{Yu_2024_BMVC,
author    = {Gao Yu and Xuchong QIU and Zihan Ye},
title     = {Effective Message Hiding with Order-Preserving Mechanisms},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0308.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection