APSIPA Transactions on Signal and Information Processing > Vol 12 > Issue 1

Green Steganalyzer: A Green Learning Approach to Image Steganalysis

Yao Zhu, University of Southern California, USA, yaozhu@usc.edu , Xinyu Wang, University of Southern California, USA, Hong-Shuo Chen, University of Southern California, USA, Ronald Salloum, California State University, USA, C.-C. Jay Kuo, University of Southern California, USA
 
Suggested Citation
Yao Zhu, Xinyu Wang, Hong-Shuo Chen, Ronald Salloum and C.-C. Jay Kuo (2023), "Green Steganalyzer: A Green Learning Approach to Image Steganalysis", APSIPA Transactions on Signal and Information Processing: Vol. 12: No. 1, e41. http://dx.doi.org/10.1561/116.00000136

Publication Date: 02 Oct 2023
© 2023 Y. Zhu, X. Wang, H.-S. Chen, R. Salloum and C.-C. Jay Kuo
 
Subjects
 
Keywords
Image SteganalysisGreen LearningSaab TransformDecision Fusion
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 326 times

In this article:
Introduction 
Review of Related Work 
Green Steganalyzer (GS) Method 
Experiments 
Conclusion and Future Work 
References 

Abstract

A novel learning solution to image steganalysis based on the green learning paradigm, called Green Steganalyzer (GS), is proposed in this work. GS consists of three modules: 1) pixel-based anomaly prediction, 2) embedding location detection, and 3) decision fusion for image-level detection. In the first module, GS decomposes an image into patches, adopts Saab transforms for feature extraction, and conducts self-supervised learning to predict an anomaly score of their center pixel. In the second module, GS analyzes the anomaly scores of a pixel and its neighborhood to find pixels of higher embedding probabilities. In the third module, GS focuses on pixels of higher embedding probabilities and fuses their anomaly scores to make final image-level classification. Compared with state-of-the-art deep-learning models, GS achieves comparable detection performance against S-UNIWARD, WOW and HILL steganography schemes with significantly lower computational complexity and a smaller model size, making it attractive for mobile/edge applications. Furthermore, GS can deal with different sized images in one single model.

DOI:10.1561/116.00000136