Efficient and Separate Authentication Image Steganography Network
Junchao Zhou, Yao Lu, Jie Wen, Guangming Lu
摘要
Image steganography hides multiple images for multiple recipients into a single cover image. All secret images are usually revealed without authentication, which reduces security among multiple recipients. It is elegant to design an authentication mechanism for isolated reception. We explore such mechanism through sufficient experiments, and uncover that additional authentication information will affect the distribution of hidden information and occupy more hiding space of the cover image. This severely decreases effectiveness and efficiency in large-capacity hiding. To overcome such a challenge, we first prove the authentication feasibility within image steganography. Then, this paper proposes an image steganography network collaborating with separate authentication and efficient scheme. Specifically, multiple pairs of lock-key are generated during hiding and revealing. Unlike traditional methods, our method has two stages to make appropriate distribution adaptation between locks and secret images, simultaneously extracting more reasonable primary information from secret images, which can release hiding space of the cover image to some extent. Furthermore, due to separate authentication, fused information can be hidden in parallel with a single network rather than traditional serial hiding with multiple networks, which can largely decrease the model size. Extensive experiments demonstrate that the proposed method achieves more secure, effective, and efficient image steganography. Code is available at https://github.com/Revive624/Authentication-Image-Steganography .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- Training-Free Coverless Multi-Image Steganography with Access ControlMinyeol Bae, Si-Hyeon LeeICML 2026
- Large-capacity and Receiver Authenticable Generative Image SteganographyJiannian Wang, Yao Lu, Guangming LuICML 2026
它引用的顶会 Paper9
- HiNet: Deep Image Hiding by Invertible NetworkJunpeng Jing, Xin Deng, Mai Xu, Jianyi Wang 等ICCV 2021 · 被引用 301 次
- Robust Invertible Image SteganographyYoumin Xu, Chong Mou, Yujie Hu, Jingfen Xie 等CVPR 2022 · 被引用 151 次
- Fixed Neural Network Steganography: Train the images, not the networkVarsha Kishore, Xiangyu Chen, Yan Wang, Boyi Li 等ICLR 2022 · 被引用 59 次
- Representational aspects of depth and conditioning in normalizing flowsFrederic Koehler, Viraj Mehta, Andrej RisteskiICML 2021 · 被引用 29 次
- Hiding Images in Deep Probabilistic ModelsHaoyu Chen, Linqi Song, Zhenxing Qian, Xinpeng Zhang 等NeurIPS 2022 · 被引用 20 次
相关 Paper
- Large-Capacity Image Steganography Based on Invertible Neural NetworksShao-Ping Lu, Rong Wang, Tao Zhong, Paul L. RosinCVPR 2021
- Large-Capacity and Flexible Video Steganography via Invertible Neural NetworkChong Mou, Youmin Xu, Jiechong Song, Chen Zhao 等CVPR 2023
- Cover-separable Fixed Neural Network Steganography via Deep Generative ModelsGuobiao Li, Sheng Li, Zhenxing Qian, Xinpeng ZhangACM MM 2024 · 被引用 15 次
- Purified and Unified Steganographic NetworkGuobiao Li, Sheng Li, Zicong Luo, Zhenxing Qian 等CVPR 2024
- Dig a Hole and Fill in Sand: Adversary and Hiding Decoupled SteganographyWeixuan Tang, Haoyu Yang, Yuan Rao, Zhili Zhou 等ACM MM 2024 · 被引用 5 次
