mlsanityData to 14 Oct 2026

Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft

arXiv 2510.07728 ↗First posted 9 Oct 2025cs.IR cs.CLcited by 15

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) by mitigating hallucinations and outdated information issues, yet simultaneously facilitates unauthorized data appropriation at scale. This paper addresses this challenge through two key contributions. First, we introduce RPD, a novel dataset specifically designed for RAG plagiarism detection that encompasses diverse professional domains and writing styles, overcoming limitations in existing resources. Second, we develop a dual-layered watermarking system that embeds protection at both semantic and lexical levels, complemented by an interrogator-detective framework that employs statistical hypothesis testing on accumulated evidence. Extensive experimentation demonstrates our approach's effectiveness across varying query volumes, defense prompts, and retrieval parameters, while maintaining resilience against adversarial evasion techniques. This work establishes a foundational framework for intellectual property protection in retrieval-augmented AI systems.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 33 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

16 of 33 references.

References · 16

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  7. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  8. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  9. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 429
  10. 2023Can AI-Generated Text be Reliably Detected?cited by 386
  11. 2023Robust Distortion-free Watermarks for Language Modelscited by 320
  12. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
4 more
  1. 2023Watermarking Text Generated by Black-Box Language Modelscited by 76
  2. 2023Black-box Membership Inference Attacks against Fine-tuned Diffusion Modelscited by 35
  3. 2024RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Contentcited by 26
  4. 2024Ward: Provable RAG Dataset Inference via LLM Watermarkscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 14.

15 papers.

Sort:

By area:

  1. 2026ExpSeek: Self-Triggered Experience Seeking for Web Agentscited by 23
  2. 2026Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrievalcited by 18
  3. 2026MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoningcited by 11
  4. 2025LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Servicescited by 8
  5. 2026Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Modelscited by 8
  6. 2026From log π to π: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weightcited by 6
  7. 2026Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertaintycited by 6
  8. 2026DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuningcited by 5
  9. 2026Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectoriescited by 4
  10. 2026Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answeringcited by 2
  11. 2026Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translationcited by 1
  12. 2026Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answeringcited by 0
3 more
  1. 2026Efficient Task Adaptation in Large Language Models via Selective Parameter Optimizationcited by 0
  2. 2026Multi-Granularity Reasoning for Natural Language Inferencecited by 0
  3. 2026Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Studycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
  2. 2026Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
  3. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
  4. 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
  5. 2026Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
  6. 2026RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
  7. 2025Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems
  8. 2026Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation