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

• URL: http://arxiv.org/abs/2608.25735v1
• Date: Wed, 26 Aug 2026 12:46:36 GMT
• Title: Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale
• Abstract summary: Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora.<n>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.<n>This shortlist short-circuits full-corpus cryptographic search without sacrificing retrieval quality.
• Score: 19.48684574323907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval [0.4859781642217615]
  We introduce Matryoshka Hash Representations (MHR), a two-stage procedure that separates full-width training from prefix organization.<n>MHR reaches.5561 NDCG@10 and.6535 Recall@100 at 32 bytes, surpassing the best baseline of the same budget.<n>The code also strengthens two common pipelines: shortlisting candidates for full-precision reranking, and pruning a low-storage graph index.
  arXiv  Detail & Related papers  (2026-09-07T09:38:28Z)
• Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings [0.4859781642217615]
  Spruce learns compact binary codes that preserve candidates for full-precision reranking.<n>Spruce preserves the original search quality with median candidate sets of only 382--1,952.<n>Private pruning takes 0.06--1.09 seconds, achieves $13.1$--$22.9times$ speedups, and retains $93.9%$--$97.3%$ of full-float NDCG.
  arXiv  Detail & Related papers  (2026-09-03T05:19:03Z)
• VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval [65.89247522243959]
  VisDocAgentBench is a closed-corpus benchmark comparing static and agentic retrieval under a ranked-output contract.<n>It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures.<n>A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query--target matching when relevance depends on corpus context.
  arXiv  Detail & Related papers  (2026-08-18T15:23:06Z)
• Efficient Privacy-Preserving Range Filtered Approximate Nearest Neighbor Search [22.644268689842377]
  Range-filtered approximate nearest neighbor search (RFANNS) is an important primitive for vector databases.<n>We formulate and evaluate privacy-preserving RFANNS over outsourced encrypted vector databases.<n>Our method improves the QPS-Recall trade-off over representative secure adaptations of existing RFANNS approaches.
  arXiv  Detail & Related papers  (2026-08-17T12:28:25Z)
• Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Research Agents [50.35041517085015]
  Existing deep-research agents use a Search--Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata.<n>We introduce textscSieve, a search--inspect-fetch strategy driven by a Boolean Query Language (BQL)<n>It searches webpage fields to filter candidates, uses an interchangeable ranker to order them, presents structure-rich result cards for inspection, and fetches only selected sections.
  arXiv  Detail & Related papers  (2026-08-03T18:01:05Z)
• MESS: Fast and Private Semantic Search on Multi-Graph HNSW [11.990611521434944]
  We present MESS, a search system with three properties: privacy, accuracy, and efficiency.<n>It maps the original vectors into binary codes, applies locality-sensitive hashing (LSH) and randomized response, and constructs a multi-graph Hierarchical Navigable Small World (HNSW) index over the perturbed codes.<n> MESS achieves up to 15.08times lower latency than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-07-31T03:53:24Z)
• Towards Retrieving Interaction Spaces for Agentic Search [62.666902610940525]
  Recent direct corpus (DCI) work shows that agents can interact with the raw corpus through shell tools such as 5.4 interaction and file reads.<n>We argue that the role of retrieval for agentic search is not just to select documents that fit in the LLM context window, but to construct an interaction space.
  arXiv  Detail & Related papers  (2026-06-05T03:47:40Z)
• GrepSeek: Training Search Agents for Direct Corpus Interaction [66.69568141699311]
  GrepSeek is an optimized direct corpus interaction (DCI) search agent that trains a compact search agent to find, filter, and compose evidence from large text corpora.<n>To make DCI practical at scale, we further use a semantics-preserving sharded-parallel execution engine that accelerates shell-based retrieval by up to $7.6times$ while preserving byte-exact equivalence with sequential execution of the shell command.
  arXiv  Detail & Related papers  (2026-05-28T03:37:33Z)
• Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets [3.5312864406384485]
  Large language models (LLMs) for code completion and generation may reproduce training examples verbatim and without authorship attribution.<n> Classical fingerprint-based plagiarism detectors based on fingerprinting, such as Winnowing, remain highly effective.<n>We introduce a 300M- parameter encoder tailored for code retrieval, together with a hybrid two-stage provenance-tracking pipeline.
  arXiv  Detail & Related papers  (2026-05-27T14:12:17Z)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction [127.64173950476702]
  We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
  arXiv  Detail & Related papers  (2026-05-03T19:13:11Z)
• Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private [21.980739918403344]
  Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving documents from an external corpus at inference time.<n>When this corpus contains sensitive information, unprotected RAG systems are at risk of leaking private information.<n>In this paper, we study the more practical multi-query setting and propose two DP-RAG algorithms.
  arXiv  Detail & Related papers  (2025-11-10T21:12:32Z)
• Accelerating Code Search with Deep Hashing and Code Classification [64.3543949306799]
  Code search is to search reusable code snippets from source code corpus based on natural languages queries. We propose a novel method CoSHC to accelerate code search with deep hashing and code classification.
  arXiv  Detail & Related papers  (2022-03-29T07:05:30Z)
• HERS: Homomorphically Encrypted Representation Search [56.87295029135185]
  We present a method to search for a probe (or query) image representation against a large gallery in the encrypted domain. Our encryption scheme is agnostic to how the fixed-length representation is obtained and can therefore be applied to any fixed-length representation in any application domain.
  arXiv  Detail & Related papers  (2020-03-27T01:10:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.