mlsanityData to 7 Oct 2026

TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization

arXiv 2607.16973 ↗First posted 18 Jul 2026cs.LG cs.AI cs.IRcited by 0

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakage channel in multi-tenant deployments, and (2) post-hoc filtering for tenant isolation degrades recall on selective queries. We study TurboVec, an open-source vector index built on TurboQuant - a codebook-oblivious scalar quantizer requiring no corpus-dependent training. On the DBpedia OpenAI embeddings benchmark (d=1536, 100K-999K vectors), TurboQuant 4-bit outperforms trained FAISS Product Quantization at the same memory budget by 8.5-8.9 percentage points in Recall@5 across all scales. Compared to HNSW (R@5=0.991) and IVF-PQ (R@5=0.840), TurboQuant occupies a distinct design point: higher recall than IVF-PQ without training, at 4-8x less memory than HNSW. Deployed on Snowpark Container Services, TurboVec achieves 11ms median query latency at 100K vectors versus 707ms for warehouse brute-force scan. Kernel-level allowlist filtering maintains 0.86-0.93 Recall@10 across 10-1000 tenant workloads versus 0.09-0.19 for post-filter baselines. Codebook-oblivious design reduces membership inference accuracy to near-random (50.0%) versus 57.3% for PQ codebooks. Limitations include single dataset evaluation, uncompressed HNSW comparison, and privacy evaluation on synthetic data only.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 26 references that are in the map. First posted on arXiv 18 Jul 2026.

Builds on

10 of 26 references.

References · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  4. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  5. 2020Information Leakage in Embedding Modelscited by 199
  6. 2025TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratecited by 116
  7. 2023Eight Things to Know about Large Language Modelscited by 73
  8. 2024RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Searchcited by 46
  9. 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Servingcited by 18
  10. 2019SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Searchcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Quantization Enables Private Dense Retrieval against Malicious Service Providers
  2. 2026π-RAG: Oblivious Retrieval via Semantic Quantization and Transcendental Addressing for Large Language Models
  3. 2026Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems
  4. 2025From HNSW to Information-Theoretic Binarization: Rethinking the Architecture of Scalable Vector Search
  5. 2026Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval
  6. 2024Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
  7. 2026Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings
  8. 2026Your Retriever Already Knows: Distribution-Shape QPP for RAG Retrieval Sufficiency