# GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG

arXiv: https://arxiv.org/abs/2607.29019 · HTML: https://mlsanity.com/paper/2607.29019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 2 of 2)

- [Efficient Ranking, Order Statistics, and Sorting under CKKS](https://mlsanity.com/paper/2412.15126/) (2024)
- [Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryption](https://mlsanity.com/paper/2601.12331/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, but existing pipelines typically operate on plaintext data, raising significant privacy concerns. Prior work on privacy-preserving retrieval leverages cryptographic techniques such as homomorphic encryption (HE) and private information retrieval (PIR), but often relies on interactive protocols or ranking-based selection mechanisms that incur high latency and potential information leakage. In this paper, we propose a practical non-interactive encrypted retrieval framework for RAG based on threshold selection. Instead of performing expensive top-k ranking under encryption, our approach selects documents whose similarity scores exceed a predefined threshold, reducing computational complexity from quadratic to linear in the corpus size. We implement this design using CKKS-based homomorphic computation, enabling fully encrypted similarity evaluation and document selection without revealing query content, intermediate scores, or selected indices. To bridge the gap between approximate encrypted computation and discrete token reconstruction, we introduce a precision-stable mask polarization method that ensures accurate recovery of selected documents. Experiments on standard retrieval benchmarks demonstrate that our approach achieves competitive retrieval effectiveness while significantly reducing latency compared to ranking-based encrypted methods. These results highlight threshold-based selection as a practical foundation for scalable and secure RAG systems.