GVIS：生成式矢量图像隐写
GVIS: Generative Vector Image Steganography
利用扩散模型生成的栅格图像经矢量化后，其贝塞尔控制点坐标可作为隐写载体；这种“生成-矢量化-差分提取”的免训练流程，为视觉研究者提供了一种把扩散采样过程当作确定性编码通道的思路，可迁移到水印、版权溯源与可控生成中的隐式信息注入。
原文依据 GVIS deterministically generates raster images using diffusion models, which are subsequently vectorized into vector images.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近年来，矢量图像因其可缩放性与结构特性，在信息隐藏领域受到越来越多的关注。然而，现有的矢量图像隐写方法往往会对文件本身引入明显的修改，从而带来潜在的安全风险并限制嵌入容量。受扩散模型与图像生成式隐写最新进展的启发，我们提出 GVIS，一种新颖的生成式矢量图像隐写框架。GVIS 利用扩散模型确定性地生成栅格图像，随后将其矢量化为矢量图像。在发送端，我们设计了一种轻量级重叠检测算法，用于识别适合嵌入数据的三次贝塞尔曲线控制点，从而将秘密信息编码到这些控制点的坐标参数中。随后，接收端可利用预先共享的设置重建生成过程，并通过差分实现精确的消息提取。大量理论分析与实验结果表明，GVIS 实现了高容量、高精度、安全且免训练的隐写。据我们所知，这是首次尝试将生成模型应用于矢量图像隐写。
英文原文摘要 1293 字符
Vector images have attracted increasing attention in the field of information hiding in recent years due to their scalability and structural properties. However, existing steganographic methods for vector images often introduce noticeable modifications to the files themselves, resulting in potential security risks and limited embedding capacity. Motivated by recent advances in diffusion models and image generative steganography, we propose GVIS, a novel Generative Vector Image Steganography framework. GVIS deterministically generates raster images using diffusion models, which are subsequently vectorized into vector images. On the sender side, we design a lightweight overlap detection algorithm to identify cubic Bezier curve control points suitable for data embedding, which enables the secret information to be encoded into the coordinate parameters of these control points. Then, the receiver can use the pre-shared settings to reconstruct the generation process and accurate message extraction by difference. Extensive theoretical analysis and experimental results demonstrate that GVIS achieves high-capacity, high-accuracy, secure, and training-free steganography. To the best of our knowledge, this is the first attempt to apply generative models to vector image steganography.