mlsanityData to 7 Oct 2026

V3DB: Audit-on-Demand Zero-Knowledge Proofs for Verifiable Vector Search over Committed Snapshots

arXiv 2603.03065 ↗First posted 3 Mar 2026cs.DBcited by 1

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

Abstract (arXiv)

Dense retrieval services increasingly underpin semantic search, recommendation, and retrieval-augmented generation, yet clients typically receive only a top-k list with no auditable evidence of how it was produced. We present V3DB, a verifiable, versioned vector-search service that enables audit-on-demand correctness checks for approximate nearest-neighbour (ANN) retrieval executed by a potentially untrusted service provider. V3DB commits to each corpus snapshot and standardises an IVF-PQ search pipeline into a fixed-shape, five-step query semantics. Given a public snapshot commitment and a query embedding, the service returns the top-k payloads and, when challenged, produces a succinct zero-knowledge proof that the output is exactly the result of executing the published semantics on the committed snapshot -- without revealing the embedding corpus or private index contents. To make proving practical, V3DB avoids costly in-circuit sorting and random access by combining multiset equality/inclusion checks with lightweight boundary conditions. Our prototype implementation based on Plonky2 achieves up to 22× faster proving and up to 40% lower peak memory consumption than the circuit-only baseline, with millisecond-level verification time. Github Repo at https://github.com/TabibitoQZP/zk-IVF-PQ.

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 11 of its 46 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

11 of 46 references.

References · 11

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  6. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  7. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  8. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  9. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
  10. 2025Overview of the TREC 2022 deep learning trackcited by 22
  11. 2024PoneglyphDB: Efficient Non-interactive Zero-Knowledge Proofs for Arbitrary SQL-Query Verificationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Atlas: Efficient Verifiable Semantic Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Unified Benchmark for Privacy-preserving Vector Search
  2. 2026Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale
  3. 2026TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization
  4. 2026Quantization Enables Private Dense Retrieval against Malicious Service Providers
  5. 2026MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
  6. 2026Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings
  7. 2026Beyond Private Training: The New Landscape of AI Privacy
  8. 2026Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval