mlsanityData to 7 Oct 2026

Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment

arXiv 2506.10030 ↗First posted 10 Jun 2025cs.CR cs.AIcited by 1

On the map: Retrieval-augmented generation → Privacy and security of RAG

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 54 of its 77 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

54 of 77 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025ControlNET: A Firewall for RAG-based LLM System13 Apr
  2. 2025MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks25 Feb
  3. 2025Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs15 Feb
  4. 2025RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models9 Jan
  5. 2024Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation18 Oct
  6. 2024TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models22 May

Other references · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2023GPT-4 Technical Reportcited by 18,132
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2025Qwen2.5-VL Technical Reportcited by 5,418
  10. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  11. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  12. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
36 more
  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  3. 2018Hierarchical Neural Story Generationcited by 1,182
  4. 2023A Watermark for Large Language Modelscited by 667
  5. 2018Spectral Signatures in Backdoor Attackscited by 457
  6. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  7. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
  8. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 237
  9. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 216
  10. 2022Re-Imagen: Retrieval-Augmented Text-to-Image Generatorcited by 208
  11. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 177
  12. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  13. 2022Retrieval-Augmented Multimodal Language Modelingcited by 125
  14. 2021WebQA: Multihop and Multimodal QAcited by 109
  15. 2023NEFTune: Noisy Embeddings Improve Instruction Finetuningcited by 99
  16. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 95
  17. 2022Retrieval Augmented Visual Question Answering with Outside Knowledgecited by 93
  18. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
  19. 2020Distortion Agnostic Deep Watermarkingcited by 88
  20. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Modelscited by 84
  21. 2024Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMscited by 79
  22. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  23. 2024RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Modelscited by 58
  24. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  25. 2024HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systemscited by 37
  26. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  27. 2024Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applicationscited by 31
  28. 2023PromptCARE: Prompt Copyright Protection by Watermark Injection and Verificationcited by 30
  29. 2023Visual Instruction Tuning towards General-Purpose Multimodal Model: A Surveycited by 28
  30. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  31. 2024Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generationcited by 23
  32. 2024Black-Box Detection of Language Model Watermarkscited by 22
  33. 2025ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generationcited by 20
  34. 2024EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generationcited by 16
  35. 2024Ward: Provable RAG Dataset Inference via LLM Watermarkscited by 15
  36. 2025Re-ranking the Context for Multimodal Retrieval Augmented Generationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SentinelRAG: Synthetic Sentinel Knowledge for RAG Database Copyright Protection
  2. 2025Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft
  3. 2025Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning
  4. 2025Removing Watermarks with Partial Regeneration using Semantic Information
  5. 2023WatME: Towards Lossless Watermarking Through Lexical Redundancy
  6. 2025VLA-Mark: A cross modal watermark for large vision-language alignment model
  7. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models
  8. 2024CPR: Retrieval Augmented Generation for Copyright Protection