mlsanityData to 14 Oct 2026

Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

arXiv 2608.25735 ↗First posted 26 Aug 2026cs.CR cs.AI cs.IRcited by 1

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

Abstract (arXiv)

Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen result, yet reveal only the documents that the user is authorized to receive. Existing cryptographic approaches either make this costly by processing the entire corpus for every query, or sacrifice quality for efficiency by scanning a few clusters. We repurpose learned deep hashing as a private filter: a randomized binary code points the provider to a short candidate list, while encrypted reranking and oblivious key transfer protect the precise query and final selection. This shortlist short-circuits full-corpus cryptographic search without sacrificing retrieval quality: with 200-500 candidates, it closely matches full-corpus retrieval across five zero-shot corpora spanning 25K to 5.4M documents. On the full 2.68M-passage NQ corpus over a 10-Gbps link, our protocol only adds 0.73 seconds, or 10 percent, to a 128-token Qwen3-32B RAG pipeline. The released code satisfies directional metric differential privacy (DP) and substantially reduces embedding-inversion and property-inference leakage, demonstrating that a carefully learned shortlist can make private dense retrieval both accurate and practical.

Key facts. Cited by 1 paper 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 51 of its 108 references that are in the map. First posted on arXiv 26 Aug 2026.

Builds on

51 of 108 references.

Closest ancestors · 5

Same direction, newest first

  1. 2026Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment23 May
  2. 2026P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval16 Mar
  3. 2026Differentially Private Retrieval-Augmented Generation16 Feb
  4. 2026Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems22 Jan
  5. 2024RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service17 Dec

Other references · 46

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2025Qwen3 Technical Reportcited by 8,820
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  9. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  10. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  11. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  12. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
34 more
  1. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  2. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  4. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  5. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 430
  6. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 218
  7. 2020Information Leakage in Embedding Modelscited by 203
  8. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 196
  9. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  10. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  11. 2015Practical and Optimal LSH for Angular Distancecited by 106
  12. 2023Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentencecited by 81
  13. 2019Central Similarity Quantization for Efficient Image and Video Retrievalcited by 77
  14. 2015Feature Learning based Deep Supervised Hashing with Pairwise Labelscited by 59
  15. 2021Efficient Passage Retrieval with Hashing for Open-domain Question Answeringcited by 53
  16. 2020A Survey on Deep Hashing Methodscited by 47
  17. 2021One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objectivecited by 43
  18. 2024Text Embedding Inversion Security for Multilingual Language Modelscited by 26
  19. 2024Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queriescited by 25
  20. 2017Hashing as Tie-Aware Learning to Rankcited by 18
  21. 2019SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Searchcited by 12
  22. 2021Private Retrieval, Computing and Learning: Recent Progress and Future Challengescited by 12
  23. 2025Universal Zero-shot Embedding Inversioncited by 8
  24. 2022Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Searchcited by 6
  25. 2020Locality Sensitive Hashing with Extended Differential Privacycited by 5
  26. 2023Don't forget private retrieval: distributed private similarity search for large language modelscited by 5
  27. 2024Metric Differential Privacy at the User-Level Via the Earth Mover's Distancecited by 5
  28. 2024How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?cited by 4
  29. 2021Obfuscated Access and Search Patterns in Searchable Encryptioncited by 2
  30. 2025A Survey on Deep Text Hashing: Efficient Semantic Text Retrieval with Binary Representationcited by 2
  31. 2026MESS: Fast and Private Semantic Search on Multi-Graph HNSWcited by 2
  32. 2025Comparing privacy notions for protection against reconstruction attacks in machine learningcited by 1
  33. 2025A Decade of Metric Differential Privacy: Advancements and Applicationscited by 1
  34. 2025Privacy-Preserving Approximate Nearest Neighbor Search on High-Dimensional Datacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Matryoshka Hash Representations for Model-Aware Compact Semantic Retrievalcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Quantization Enables Private Dense Retrieval against Malicious Service Providers
  2. 2026PILLAR: Private Inverted-Index Lexical Lookup for Augmented Retrieval
  3. 2026Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings
  4. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
  5. 2026PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation
  6. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
  7. 2026GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG
  8. 2026π-RAG: Oblivious Retrieval via Semantic Quantization and Transcendental Addressing for Large Language Models