arXiv 论文提出覆盖直接生成与代码渲染两条路径的视觉溯源检测与水印框架
Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering
想搞 AI 内容水印的可以看看，这篇把 LLM 写代码渲染这条路线也纳入了溯源框架，还列了十个具体研究方向。
一篇 arXiv 论文系统比较了图像/视频的两条生成路径：直接用生成模型产出，以及由 LLM 写代码或图形描述再渲染。作者提出以生产流程为中心的框架，把图像、视频、源代码和渲染感知水印按生产阶段分类，并用明确的验证规范区分被动推断、消息恢复和认证溯源。论文引用了 Claude、OpenAI 和渲染工具的公开接口来落地到具体系统，并提出十个范围明确的研究问题，涵盖可识别性、载荷恢复、同步、组合等方向。论文本身不含实验，定位为基于已有方法和接口审查的研究议程。
Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering
AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These routes can produce similar visible artifacts but expose different representations, intervention points, and provenance evidence. We develop a production-centered framework that compares detection and watermarking across both routes. An explicit verification specification distinguishes passive inference, message recovery, and authenticated provenance. We organize image, video, source-code, and rendering-aware watermarks by production stage. We examine the different requirements of generated images and video, plots and SVG, programmable video, and agent-composed workflows. Documented Claude, OpenAI, and rendering-tool interfaces connect the framework to concrete systems. We pose ten scoped research questions on identifiability, observability, fair comparison across stages, recoverable payload, reconstruction, synchronization, composition, hybrid local contribution, and private production-event authentication. The result is a conceptual research agenda grounded in published methods, inspected interfaces, and elementary boundary examples. It reports no experiments and claims no new theorems; its appendix results are elementary calculations, and documentation and source inspection establish interfaces, not empirical robustness.
