mlsanityData to 14 Oct 2026

A Case Study on the Impact of Anonymization Along the RAG Pipeline

arXiv 2604.15958 ↗First posted 17 Apr 2026cs.CR cs.CLcited by 0

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

Abstract (arXiv)

Despite the considerable promise of Retrieval-Augmented Generation (RAG), many real-world use cases may create privacy concerns, where the purported utility of RAG-enabled insights comes at the risk of exposing private information to either the LLM or the end user requesting the response. As a potential mitigation, using anonymization techniques to remove personally identifiable information (PII) and other sensitive markers in the underlying data represents a practical and sensible course of action for RAG administrators. Despite a wealth of literature on the topic, no works consider the placement of anonymization along the RAG pipeline, i.e., asking the question, where should anonymization happen? In this case study, we systematically and empirically measure the impact of anonymization at two important points along the RAG pipeline: the dataset and generated answer. We show that differences in privacy-utility trade-offs can be observed depending on where anonymization took place, demonstrating the significance of privacy risk mitigation placement in RAG.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 41 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

23 of 41 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryption18 Jan
  2. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems7 Jan
  3. 2025Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems30 May
  4. 2024RAG with Differential Privacy26 Dec
  5. 2024RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service17 Dec
  6. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data20 Jun
  7. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 16

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  3. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  4. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  5. 2022The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymizationcited by 95
  6. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  7. 2023Locally Differentially Private Document Generation Using Zero Shot Promptingcited by 63
  8. 2024Knowledge Boundary of Large Language Models: A Surveycited by 40
  9. 2023Privacy Implications of Retrieval-Based Language Modelscited by 32
  10. 2024Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreakingcited by 30
  11. 2024DP-MLM: Differentially Private Text Rewriting Using Masked Language Modelscited by 24
  12. 2024Unique Security and Privacy Threats of Large Language Models: A Comprehensive Surveycited by 23
4 more
  1. 2024Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Modelscited by 21
  2. 2022Differential Privacy in Natural Language Processing: The Story So Farcited by 12
  3. 20241-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacycited by 10
  4. 2025On the Impact of Noise in Differentially Private Text Rewritingcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Not All Entities are Created Equal: A Dynamic Anonymization Framework for Privacy-Preserving RAG
  2. 2026Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs
  3. 2026RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
  4. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
  5. 2025Exposing Privacy Risks in Graph Retrieval-Augmented Generation
  6. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
  7. 2026Is External Database Protection Static in Retrieval-Augmented Generation? Rethinking Privacy Preservation under Dynamic Queries
  8. 2026Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks