arXiv AI September 7, 2026 By Xinguo Feng, Zhongkui Ma, Zihan Wang, Chuan Yan, Guowei Yang, Alsharif Abuadbba, Guangdong Bai

Shadow Queries for Private Retrieval in Vector Databases

Read the original on arXiv AI →

The paper introduces SHAQ, a defense called Shadow Query Generation that protects document embeddings in vector databases from embedding inversion attacks. SHAQ replaces direct embeddings with diverse shadow queries generated by a language model, thereby decomposing document semantics and decoupling stored embeddings from the original text. Experiments on various IR datasets show that SHAQ significantly lowers recovery rates, defends more tokens than baseline methods, and even improves retrieval utility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 3

Embedding Inference Attack

arXiv:2607. 01276v1 Announce Type: cross Abstract: Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs.

By Cedric Fitiavana Raelijohn, S\'ebastien Gambs, Jean-Francois Rajotte

llms rag

arXiv AI

Jun 26

Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model

arXiv:2606. 26373v1 Announce Type: cross Abstract: Dense embeddings power semantic search and retrieval-augmented generation, but embedding-inversion attacks can reconstruct source text from a vector: when a vector database leaks, the documents behind it leak too.

By Sergey Kurilenko

rag efficiency benchmarks safety

arXiv Computation and Language

Aug 31

CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents

arXiv:2608. 28389v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers.

By Jaewon Jung, Haizhong Zheng, Hongsun Jang, Jaeyong Song, Beidi Chen, Jinho Lee

llms rag multimodal benchmarks safety

arXiv Machine Learning

Aug 27

Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

The paper presents a practical private dense retrieval system that uses learned deep hashing as a private filter to generate a short candidate list for each query. Encrypted reranking and oblivious key transfer protect the exact query and final selection, allowing the system to match full‑corpus retrieval quality with only 200‑500 candidates. Experiments on five zero‑shot corpora and the 2.68M‑passage NQ corpus show minimal latency overhead and strong privacy guarantees.

By Peichun Hua, Danyang Chen, Junan Zhang, Haifeng Sun, Jingyu Wang, Diwen Xue, Mingyu Li, Yunming Xiao

rag safety

arXiv AI

Aug 14

Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs

arXiv:2608. 12675v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries.

By Saleh Almohaimeed, Saad Almohaimeed, Mousa Jari, Fahad Alotaibi, Khalid A. Alobaid

llms rag fine-tuning safety

Hugging Face Trending Papers

Aug 26

Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen result, yet reveal onl...

rag safety

One email a morning, machine-written

Related stories

Embedding Inference Attack

Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model

CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents

Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs

Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale