Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.01331 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909010124341248 |
|---|---|
| author | Wang, Hao Yao, Yiming Xie, Yaguang Qiao, Tong Zhao, Zhidong |
| author_facet | Wang, Hao Yao, Yiming Xie, Yaguang Qiao, Tong Zhao, Zhidong |
| contents | Image steganalysis, which aims at detecting secret information concealed within images, has become a critical countermeasure for assessing the security of steganography methods, especially the emerging invertible image hiding approaches. However, prior studies merely classify input images into two categories (i.e., stego or cover) and typically conduct steganalysis under the constraint that training and testing data must follow similar distribution, thereby hindering their application in real-world scenarios. To overcome these shortcomings, we propose a novel interpretable image steganalysis framework tailored for invertible image hiding schemes under a challenging zero-shot setting. Specifically, we integrate image hiding, revealing, and steganalysis into a unified framework, endowing the steganalysis component with the capability to recover the secret information embedded in stego images. Additionally, we elaborate a simple yet effective residual augmentation strategy for generating stego images to further enhance the generalizability of the steganalyzer in cross-dataset and cross-architecture scenarios. Extensive experiments on benchmark datasets demonstrate that our proposed approach significantly outperforms the existing steganalysis techniques for invertible image hiding schemes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01331 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Zero-Shot Interpretable Image Steganalysis for Invertible Image Hiding Wang, Hao Yao, Yiming Xie, Yaguang Qiao, Tong Zhao, Zhidong Computer Vision and Pattern Recognition Image steganalysis, which aims at detecting secret information concealed within images, has become a critical countermeasure for assessing the security of steganography methods, especially the emerging invertible image hiding approaches. However, prior studies merely classify input images into two categories (i.e., stego or cover) and typically conduct steganalysis under the constraint that training and testing data must follow similar distribution, thereby hindering their application in real-world scenarios. To overcome these shortcomings, we propose a novel interpretable image steganalysis framework tailored for invertible image hiding schemes under a challenging zero-shot setting. Specifically, we integrate image hiding, revealing, and steganalysis into a unified framework, endowing the steganalysis component with the capability to recover the secret information embedded in stego images. Additionally, we elaborate a simple yet effective residual augmentation strategy for generating stego images to further enhance the generalizability of the steganalyzer in cross-dataset and cross-architecture scenarios. Extensive experiments on benchmark datasets demonstrate that our proposed approach significantly outperforms the existing steganalysis techniques for invertible image hiding schemes. |
| title | Zero-Shot Interpretable Image Steganalysis for Invertible Image Hiding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.01331 |