Guoliang Xie
Self-attention enhanced deep residual network for spatial image steganalysis.
Xie, Guoliang; Ren, Jinchang; Marshall, Stephen; Zhao, Huimin; Li, Rui; Chen, Rongjun
Authors
Professor Jinchang Ren j.ren@rgu.ac.uk
Professor of Computing Science
Stephen Marshall
Huimin Zhao
Rui Li
Rongjun Chen
Abstract
As a specially designed tool and technique for the detection of image steganography, image steganalysis conceals information under the carriers for covert communications. Being developed on the BOSSbase dataset and released a decade ago, most of the Convolutional Neural Network (CNN) architectures for spatial image steganalysis fail to achieve satisfactory performance on new challenging datasets, i.e. ALASKA#2, which was released recently and is more complex yet consistent with the real scenarios. In this paper, we propose an enhanced residual network (ERANet) with self-attention ability, which utilizes a more complex residual method and a global self-attention technique, to alleviate the problem. Compared to the residual network that was widely used in the state-of-the-art, the enhanced residual network mathematically employed a more sophisticated way to extract more effective features in the images and hence it is suitable for more complex situations in the new dataset. Our proposed Enhanced Low-Level Feature Representation Module can be easily mounted on other CNNs in selecting the most representative features. Although it comes with a slightly extra computational cost, comprehensive experiments on the BOSSbase and ALASKA#2 datasets at various sizes have demonstrated the effectiveness of the proposed methodology. In short, ERANet provides an improvement of about 3.77% on average, compared to a few state-of-the-art CNNs.
Citation
XIE, G., REN, J., MARSHALL, S., ZHAO, H., LI, R. and CHEN, R. 2023. Self-attention enhanced deep residual network for spatial image steganalysis. Digital signal processing [online], 139, article 104063. Available from: https://doi.org/10.1016/j.dsp.2023.104063
Journal Article Type | Article |
---|---|
Acceptance Date | May 10, 2023 |
Online Publication Date | May 25, 2023 |
Publication Date | Jul 31, 2023 |
Deposit Date | May 19, 2023 |
Publicly Available Date | May 26, 2024 |
Journal | Digital signal processing |
Print ISSN | 1051-2004 |
Electronic ISSN | 1095-4333 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 139 |
Article Number | 104063 |
DOI | https://doi.org/10.1016/j.dsp.2023.104063 |
Keywords | Image steganography; Spatial image steganalysis; Res2Net; BoTNet; Convolutional Neural Network (CNN) |
Public URL | https://rgu-repository.worktribe.com/output/1961803 |
Files
XIE 2023 Self-attention enhanced
(1.8 Mb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by-nc-nd/4.0/
You might also like
Two-click based fast small object annotation in remote sensing images.
(2024)
Journal Article
Prompting-to-distill semantic knowledge for few-shot learning.
(2024)
Journal Article
Detection-driven exposure-correction network for nighttime drone-view object detection.
(2024)
Journal Article
Feature aggregation and region-aware learning for detection of splicing forgery.
(2024)
Journal Article
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search