‹ back to 2026-08-27

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

arXiv cs.CR LLM Agents Peichun Hua, Danyang Chen, Junan Zhang, Haifeng Sun, Jingyu Wang, Diwen Xue, Mingyu Li, Yunming Xiao 2026-08-26

TL;DR - This paper presents a privacy-preserving dense retrieval protocol for hosted RAG and semantic search that uses learned deep hashing to privately narrow searches before encrypted reranking. It approaches full-corpus retrieval quality while adding only 0.73 seconds to a Qwen3-32B RAG pipeline on a 2.68M-passage corpus.

Randomized binary codes produce short candidate lists while hiding queries and reducing full-corpus cryptographic computation.
Encrypted reranking and oblivious key transfer protect the exact query, selected result, and access authorization.
Shortlists of 200–500 candidates closely match full-corpus retrieval across five zero-shot datasets ranging from 25K to 5.4M documents.
The released implementation satisfies directional metric differential privacy and reduces embedding-inversion and property-inference leakage.

view merged work →