PRAG delivers end-to-end private RAG with 72-74% recall via non-interactive homomorphic approximations, interactive client assistance, and operation-error estimation to preserve ranking quality.
The good and the bad: Exploring privacy issues in retrieval-augmented generation (rag)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
GuarantRAG improves RAG accuracy up to 12.1% and cuts hallucinations 16.3% by decoupling parametric reasoning from evidence integration via contrastive DPO and joint decoding.
citing papers explorer
-
PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation
PRAG delivers end-to-end private RAG with 72-74% recall via non-interactive homomorphic approximations, interactive client assistance, and operation-error estimation to preserve ranking quality.
-
ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
-
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
GuarantRAG improves RAG accuracy up to 12.1% and cuts hallucinations 16.3% by decoupling parametric reasoning from evidence integration via contrastive DPO and joint decoding.