GSF 提出「可再版溯源」框架:跨版本追踪图像水印授权状态
Image Watermarking With Memory Across Reissuance
AI 导读
一篇 arXiv 论文提出 Generational Stratigraphy Fields(GSF),形式化「可再版溯源」问题:判定图像当前、已被取代或未发布状态,并恢复每个区域最后授权的版本。
正文 · 原文
Abstract:Publishers often revise and reissue images, yet valid watermarks may persist on superseded releases or unapproved edits. Even a current release can contain regions last authorized at different revisions. We introduce and formalize reissuable provenance: determining an image's current, superseded, or unissued status and recovering each region's last authorized revision (its generation), with abstention when evidence is insufficient. Generational Stratigraphy Fields (GSF) combine watermark evidence with an authenticated live reference to the current release, enabling replacement or retirement without rewriting circulated copies. Each reissue freshly embeds new generation labels in approved regions and inherited labels elsewhere, preserving history without requiring old watermarks to survive successive edits. Our complete-output reissuance evaluation follows 480 histories through four releases, retaining each AI editor's entire output. GSF achieves 99.67% accuracy in classifying issued images as current or superseded and 94.09% recall of unissued edits. After three reissues, one generation map provides time and location: it recovers regional labels with 93.13% median accuracy and localizes the latest approved revision with 92.86% IoU. Regional labels remain readable under tested delivery transformations that impair issued-state recognition. Watermarks can thus express who issued an image, which release is authoritative now, and when each region was last authorized.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23363 [cs.CR] |
| (or arXiv:2611.23363v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23363 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yi Nian [view email]
[v1]
Tue, 17 Nov 2026 17:51:38 UTC (35,528 KB)
来源:arXiv cs.AI · arxiv.org