As Retrieval-Augmented Generation (RAG) evolves into service-oriented platforms (Rag-as-a-Service) with shared knowledge bases, protecting the copyright of contributed data becomes essential. Existing watermarking methods in RAG focus solely on textual knowledge, leaving image knowledge unprotected. In this work, we propose AQUA, the first watermark framework for image knowledge protection in Multimodal RAG systems. AQUA embeds semantic signals into synthetic images using two complementary methods: acronym-based triggers and spatial relationship cues. These techniques ensure watermark signals survive indirect watermark propagation from image retriever to textual generator, being efficient, effective and imperceptible. Experiments across diverse models and datasets show that AQUA enables robust, stealthy, and reliable copyright tracing, filling a key gap in multimodal RAG protection.

翻译：随着检索增强生成（RAG）向共享知识库的服务化平台（RAG-as-a-Service）演进，保护贡献数据的版权变得至关重要。现有RAG中的水印方法仅关注文本知识，导致图像知识处于无保护状态。本研究提出AQUA，首个面向多模态RAG系统中图像知识保护的水印框架。AQUA通过两种互补方法将语义信号嵌入合成图像：基于首字母缩写的触发机制与空间关系提示。这些技术确保水印信号能够经受从图像检索器到文本生成器的间接水印传播过程，具备高效性、有效性与不可感知性。在多种模型与数据集上的实验表明，AQUA能实现鲁棒、隐蔽且可靠的版权追溯，填补了多模态RAG保护领域的关键空白。