Metraipolis › archive › dc_ee786ae3c5c7
Shadow Queries for Private Retrieval in Vector Databases — arXiv:2609.04767
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04767
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:20:53.451Z
- SHA-256 of the archived text
01bec8ecfa0950ed3fafc453b1bd0cef534d0c299eb8871031d04e4681207605- Stable URL of this page
https://metraipolis.com/documento/dc_ee786ae3c5c7
How to cite
Shadow Queries for Private Retrieval in Vector Databases — arXiv:2609.04767 — arXiv (en), https://arxiv.org/abs/2609.04767 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee786ae3c5c7 (Metraipolis archive dc_ee786ae3c5c7, sha256 01bec8ecfa0950ed3fafc453b1bd0cef534d0c299eb8871031d04e4681207605)
BibTeX
@misc{dcee786ae3c5c7,
title = {Shadow Queries for Private Retrieval in Vector Databases — arXiv:2609.04767},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04767},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee786ae3c5c7; sha256 01bec8ecfa0950ed3fafc453b1bd0cef534d0c299eb8871031d04e4681207605},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04767. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) increasingly rely on information retrieval (IR) systems, such as Retrieval-Augmented Generation (RAG), to incorporate domain-specific knowledge without costly re-training. These systems often store pre-computed document embeddings in cloud-based vector databases. However, such embeddings are vulnerable to embedding inversion attacks (EIAs), which can reconstruct their underlying text. Existing defenses, such as adding noise or scaling embeddings, often provide limited privacy or significantly reduce retrieval utility. We propose SHAQ (shadow query generation), a semantic-decomposition and embedding-decoupling defense against EIAs. SHAQ is based on the insight that EIAs rely on the strong coupling between an embedding and its original text. Instead of storing document embeddings directly, SHAQ uses a generative language model to create diverse shadow queries that capture different semantic aspects of each document. These queries are then encoded and stored in place of the original document embeddings, thereby decomposing document semantics and decoupling stored embeddings from the source text. Experiments across diverse IR datasets show that SHAQ substantially improves privacy while preserving retrieval utility, achieving a recovery rate as low as 0.2104, defending up to 19.50% more tokens than baseline defenses, and reaching up to 0.7967 MAP@10 with up to 5.53% utility improvement. These results demonstrate that semantic decomposition and embedding decoupling provide an effective alternative to directly modifying embeddings for defending against EIAs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.04767 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T22:18:11.387Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).