Shadow Queries for Private Retrieval in Vector Databases

• URL: http://arxiv.org/abs/2609.04767v1
• Date: Fri, 04 Sep 2026 05:59:54 GMT
• Title: Shadow Queries for Private Retrieval in Vector Databases
• Abstract summary: We propose SHAQ, a semantic-decomposition and embedding-decoupling defense against embedding inversion attacks (EIAs)<n>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.<n>Experiments show that SHAQ substantially improves privacy while preserving retrieval utility.
• Score: 22.541206283544586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection [82.2968697030677]
  Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts.<n>We propose Reward-Guided Semantic Evolution (RGSE), a training-free framework that directly refines the text embeddings at test time.
  arXiv  Detail & Related papers  (2026-05-06T06:17:41Z)
• Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation [61.47019392413271]
  WinnowRAG is designed to systematically filter out noisy documents while preserving valuable content.<n>WinnowRAG operates in two stages: In Stage I, we perform query-aware clustering to group similar documents and form distinct topic clusters.<n>In Stage II, we perform winnowing, wherein a critic LLM evaluates the outputs of multiple agents and iteratively separates useful documents from noisy ones.
  arXiv  Detail & Related papers  (2025-11-01T20:08:13Z)
• Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment [7.491164990682839]
  STEER (textbfSecure textbfTransformed textbfEmbedding vtextbfEctortextbf Retrieval) is a private vector retrieval framework.<n>It safeguards query text privacy while maintaining the retrieval accuracy.
  arXiv  Detail & Related papers  (2025-07-24T15:41:34Z)
• Safeguarding LLM Embeddings in End-Cloud Collaboration via Entropy-Driven Perturbation [16.419373701694067]
  EntroGuard is an entropy-driven embedding privacy protection method.<n>It can protect the privacy of text embeddings while maintaining retrieval accuracy during the end-cloud collaboration.
  arXiv  Detail & Related papers  (2025-03-17T07:58:05Z)
• From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants [28.149173430599525]
  We use a Retrieval-Augmented Generation (RAG) framework powered by a Knowledge Graph (KG) to retrieve relevant information from external knowledge sources.<n>Our KG-RAG system retrieves relevant provenances, which are added to the user prompts context before being sent to the LLM generating the response.<n>Our evaluation demonstrates that this approach significantly enhances response relevance, reducing irrelevant answers by over 50% and increasing fully relevant answers by 88% compared to the existing production system.
  arXiv  Detail & Related papers  (2025-02-21T06:22:12Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation [9.220337458064765]
  We present a Few-shot Textual Embedding Inversion Attack using ALignment and GENeration (ALGEN)<n>We find that ALGEN attacks can be effectively transferred across domains and languages, revealing key information.<n>We establish a new textual embedding inversion paradigm with broader applications for embedding alignment in NLP.
  arXiv  Detail & Related papers  (2025-02-16T23:11:13Z)
• Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs [67.0310240737424]
  We introduce a novel approach to safeguard the ownership of text datasets and effectively detect unauthorized use by the RA-LLMs.<n>Our approach preserves the original data completely unchanged while protecting it by inserting specifically designed canary documents into the IP dataset.<n>During the detection process, unauthorized usage is identified by querying the canary documents and analyzing the responses of RA-LLMs.
  arXiv  Detail & Related papers  (2025-02-15T04:56:45Z)
• Multi-Facet Blending for Faceted Query-by-Example Retrieval [5.156059061769101]
  We propose a multi-facet blending (FaBle) augmentation method, which exploits modularity by decomposing and recomposing to explicitly synthesize facet-specific training sets.<n>Our modularization eliminates the need for pre-defined facet knowledge or labels.<n>FaBle augmentation on 1K documents remarkably assists training in obtaining facet conditional embeddings.
  arXiv  Detail & Related papers  (2024-12-02T12:32:19Z)
• Contextual Document Embeddings [77.22328616983417]
  We propose two complementary methods for contextualized document embeddings. First, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss. Second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation.
  arXiv  Detail & Related papers  (2024-10-03T14:33:34Z)
• Precise Zero-Shot Dense Retrieval without Relevance Labels [60.457378374671656]
  Hypothetical Document Embeddings(HyDE) is a zero-shot dense retrieval system. We show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever.
  arXiv  Detail & Related papers  (2022-12-20T18:09:52Z)

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.