StegaPos：通过不可感知的位置嵌入防止不需要的裁剪和替换
StegaPos: Preventing Unwanted Crops and Replacements with Imperceptible Positional Embeddings
摘要：
我们提出了一个学习，空间变化的隐写系统，允许检测何时以及如何图像已被修改后，裁剪，拼接或修复出版。该系统包括：学习编码器，其在发布之前在每个局部图像区域中不可感知地隐藏不同的位置签名;以及伴随的学习解码器，其提取隐写签名以针对每个局部图像区域确定其在原始发布的图像内的2D位置坐标。裁剪和替换编辑可以通过它们在隐藏的位置签名中引起的不一致来检测。使用小型$(400 \times 400)$图像的原型系统，我们通过实验证明，简单的CNN编码器和解码器架构可以联合训练，以实现可靠和鲁棒的检测，而不会引入可感知的失真。这种方法可以帮助个人和图像共享平台证明图像是由可信来源发布的，并且还可以知道这种图像的哪些部分（如果有的话）自发布以来已经被大幅修改。
英文摘要：
We present a learned, spatially-varying steganography system that allows detecting when and how images have been altered by cropping, splicing or inpainting after publication. The system comprises a learned encoder that imperceptibly hides distinct positional signatures in every local image region before publication, and an accompanying learned decoder that extracts the steganographic signatures to determine, for each local image region, its 2D positional coordinates within the originally-published image. Crop and replacement edits become detectable by the inconsistencies they cause in the hidden positional signatures. Using a prototype system for small $(400 \times 400)$ images, we show experimentally that simple CNN encoder and decoder architectures can be trained jointly to achieve detection that is reliable and robust, without introducing perceptible distortion. This approach could help individuals and image-sharing platforms certify that an image was published by a trusted source, and also know which parts of such an image, if any, have been substantially altered since publication.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
