Private Retrieval Augmented Generation via Random Projection

arXiv:2610.22297v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it can also introduce privacy risks by leaking sensitive information from the retrieval datastore. We propose a simple method to preserve datastore privacy in RAG systems via random projection. By applying the same projection to both datastore embeddings and query embeddings, our method provably preserves semantic similarity between queries and retrieved items while substantially mitigating data extraction attacks. Across multiple RAG architectures and datasets, we show that this lightweight approach achieves superior retrieval and generation performance compared to prior methods which leverage formal differential privacy (DP) guarantees, while exhibiting comparable empirical privacy under strong attack models. Our results for the first time suggest that random projection can serve as a competitive and practical baseline for privacy-preserving RAG systems.

Related

• Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
• Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game
• Shadow Queries for Private Retrieval in Vector Databases
• E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems

Source: arXiv cs.AI | 2026-10-16