With the rapid development of AIGC technologies, generative image steganography has attracted increasing attention due to its high imperceptibility and flexibility. However, existing generative steganography methods often maintain acceptable security and robustness only at relatively low embedding rates, severely limiting the practical applicability of steganographic systems. To address this issue, we propose a novel DTAMS framework that achieves high embedding rates while ensuring strong robustness and security. Specifically, a dynamic multi-timestep adaptive embedding mechanism is constructed based on transition-cost modeling in diffusion models, enabling automatic selection of optimal embedding timesteps to improve embedding rates while preserving overall performance. Meanwhile, we propose a global sub-interval mapping strategy that jointly considers mapping errors and the frequency distribution of secret information, converting point-wise perturbations into interval-level statistical mappings to suppress error accumulation and distribution drift during multi-step diffusion processes. Furthermore, a multi-dimensional joint constraint mechanism is introduced to mitigate distortions caused by repeated latent-pixel transformations by jointly regularizing embedding errors at the pixel, latent, and semantic levels. Experiments demonstrate that the proposed method achieves an embedding rate of 12 bpp while maintaining excellent security and robustness. Across all evaluated conditions, DTAMS reduces the average extraction error rate by 59.39%, representing a significant improvement over SOTA methods.

翻译：随着AIGC技术的快速发展，生成式图像隐写术因其高隐蔽性和灵活性而受到越来越多的关注。然而，现有的生成式隐写方法往往只能在相对较低的嵌入率下保持可接受的安全性和鲁棒性，严重限制了隐写系统的实际适用性。为解决这一问题，我们提出了一种新颖的DTAMS框架，该框架在确保强鲁棒性和安全性的同时实现了高嵌入率。具体而言，基于扩散模型中的转移成本建模，构建了一种动态多时间步自适应嵌入机制，能够自动选择最优嵌入时间步，在保持整体性能的同时提高嵌入率。同时，我们提出了一种全局子区间映射策略，该策略联合考虑映射误差和秘密信息的频率分布，将逐点扰动转换为区间级统计映射，以抑制多步扩散过程中的误差累积和分布漂移。此外，引入了一种多维联合约束机制，通过在像素、潜在和语义层面联合正则化嵌入误差，以减轻由重复的潜在-像素变换引起的失真。实验表明，所提方法在保持优异安全性和鲁棒性的同时，实现了12 bpp的嵌入率。在所有评估条件下，DTAMS将平均提取错误率降低了59.39%，相较于SOTA方法有显著提升。