| 摘要: |
| 传统图像隐写术通过将秘密信息嵌入载体图像中实现信息隐蔽传输, 在信息安全和数据通信领域发挥着重要作用. 然而, 信息嵌入过程不可避免地会修改载体图像, 容易被隐写分析工具检测到. 相比之下, 生成式图像隐写术利用生成模型直接从秘密信息生成隐写图像, 从而避免了修改载体图像的问题. 但现有生成式图像隐写方法在面对各种攻击尤其是几何攻击时普遍存在鲁棒性不足的缺陷, 隐藏的信息易受各种攻击破坏而无法有效提取. 为此, 提出一种人体姿态引导的生成式隐写(generative steganography guided by human posture, GSHP)方法. 该方法的核心思想是将秘密信息映射为人体姿态特征, 再将此特征输入生成模型以生成隐写图像. 在信息提取阶段, 通过人体姿态检测算法识别隐写图像中的人体姿态, 进而还原出秘密信息. 由于人体姿态固有的结构稳定性, GSHP对各种攻击表现出了良好的鲁棒性. 广泛的实验也充分证明了GSHP在安全性和鲁棒性方面的优势. |
| 关键词: 生成式隐写 鲁棒隐写 人体姿态 几何不变性 扩散模型 |
| DOI：10.13328/j.cnki.jos.007662 |
| 分类号: |
| 基金项目:国家自然科学基金(U2336208, 62472454, 62272255); 深圳市科技计划(JCYJ20250604175534044); 算力互联网与信息安全教育部重点实验室开放课题(2024ZD022) |
|
| Robust Generative Steganography Guided by Human Posture |
|
ZHANG Qing-Hua1,2, HUANG Fang-Jun1,2, MA Bin3
|
|
1.School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen 518107, China;2.Guangdong Provincial Key Laboratory of Information Security Technology, Guangzhou 510006, China;3.Key Laboratory of Computing Power Network and Information Security (Qilu University of Technology (Shandong Academy of Sciences)), Ministry of Education, Jinan 250353, China
|
| Abstract: |
| Traditional image steganography achieves covert information transmission by embedding secret information into cover images, playing a crucial role in information security and data communication. However, the information embedding process inevitably alters the cover image, making it more susceptible to detection by steganalysis tools. In contrast, generative image steganography directly synthesizes stego images from secret information using generative models, avoiding modifications to cover images. Nevertheless, existing generative image steganography methods generally suffer from insufficient robustness against various attacks, particularly geometric attacks, often resulting in damage to the hidden information and failure to effectively extract it. To address this issue, this study proposes a generative steganography method guided by human posture (GSHP). The core idea is to map secret information into human posture features, which are then fed into a generative model to produce stego images. During the information extraction stage, a human posture detection algorithm is used to identify the posture in the stego image, thus recovering the hidden information. Owing to the inherent structural stability of human posture, GSHP exhibits good robustness against various attacks. Extensive experiments also fully demonstrate the advantages of GSHP in terms of security and robustness. |
| Key words: generative steganography robust steganography human posture geometric invariance diffusion model |
