$p^2$RAG: Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval

ArXi:2603.14778v1 Announce Type: cross Retrieval-Augmented Generation (RAG) enables large language models to use external knowledge, but outsourcing the RAG service raises privacy concerns for both data owners and users. Privacy-preserving RAG systems address these concerns by performing secure top-$k$ retrieval, which typically is secure sorting to identify relevant documents. However, existing systems face challenges ing arbitrary $k$ due to their inability to change $k$, new security issues, or efficiency degradation with large $k