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

2026-03-03

AI Summary

This work addresses the lack of auditability in existing dense retrieval systems, where clients cannot verify the correctness of returned top-k results. The authors propose the first verifiable vector search service supporting on-demand auditing by formalizing the IVF-PQ retrieval process into a fixed five-step query semantics. Their approach combines cryptographic commitments with multiset equivalence and inclusion checks to efficiently generate succinct zero-knowledge proofs—avoiding expensive in-circuit sorting and random memory accesses. Implemented atop Plonky2, the prototype maintains result correctness while achieving up to 22× speedup over a pure circuit baseline, reducing peak memory usage by 40%, and enabling verification latency in the millisecond range.

Technology Category

• Computer Vision: Image and Video Retrieval
• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

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 $22\times$ 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.

Problem

• verifiable vector search
• zero-knowledge proofs
• audit-on-demand
• committed snapshots
• approximate nearest-neighbour retrieval

Innovation

• zero-knowledge proof
• verifiable vector search
• committed snapshots
• IVF-PQ
• audit-on-demand