用扩散模型实现可控制的隐写，信息嵌入零失真且100%可恢复。
Shackled Dancing: A Bit-Locked Diffusion Algorithm for Lossless and Controllable Image Steganography
- 通过位位置锁定与采样注入，让生成过程可控嵌入信息
- 信息恢复准确率100%，在安全、容量和画质间取得平衡
- 适合需要高安全性视觉通信的研究者与应用开发者
隐写旨在将信息隐藏于视觉内容中，但现有空域与频域方法在安全性、容量与感知质量间存在权衡。生成模型（尤其是扩散模型）为自适应图像合成提供了新路径，但如何精确嵌入信息仍具挑战。本文提出一种即插即用的生成隐写方法Shackled Dancing Diffusion（SD²），结合位位置锁定与扩散采样注入，在生成轨迹中实现可控信息嵌入。该方法利用扩散模型的强大表达能力生成多样化载体图像，同时保证信息可完全恢复（100%准确率）。所提算法在随机性与约束间取得良好平衡，增强抗隐写分析能力，且不损害图像保真度。大量实验表明，SD²在安全性、嵌入容量与稳定性上显著优于现有方法。该算法为可控生成提供了新视角，并为安全视觉通信开辟了新方向。
原文摘要 · Abstract (English)
Data steganography aims to conceal information within visual content, yet existing spatial- and frequency-domain approaches suffer from trade-offs between security, capacity, and perceptual quality. Recent advances in generative models, particularly diffusion models, offer new avenues for adaptive image synthesis, but integrating precise information embedding into the generative process remains challenging. We introduce Shackled Dancing Diffusion, or SD$^2$, a plug-and-play generative steganography method that combines bit-position locking with diffusion sampling injection to enable controllable information embedding within the generative trajectory. SD$^2$ leverages the expressive power of diffusion models to synthesize diverse carrier images while maintaining full message recovery with $100\%$ accuracy. Our method achieves a favorable balance between randomness and constraint, enhancing robustness against steganalysis without compromising image fidelity. Extensive experiments show that SD$^2$ substantially outperforms prior methods in security, embedding capacity, and stability. This algorithm offers new insights into controllable generation and opens promising directions for secure visual communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。