让分布式数据中的大模型检索更安全，支持隐私保护下的远程推理。
Supercharging Federated Intelligence Retrieval
- 本地化文档检索，服务器仅聚合结果并生成文本
- 在可信环境中运行推理，防御好奇或被攻破的服务器
- 可接入第三方非密模型作辅助，不泄露敏感信息
传统检索增强生成（RAG）依赖集中式文档访问，在知识分散于私有数据孤岛时失效。本文提出基于Flower的联邦RAG系统，实现本地孤岛检索，同时将服务器端的聚合与文本生成置于经验证的机密计算环境中，即使面对诚实但好奇或已受损的服务器，也能保障远程大模型推理的机密性。此外，我们设计了一种级联推理方法，可引入非机密第三方模型（如Amazon Nova）作为辅助上下文，而不降低整体保密性。
原文摘要 · Abstract (English)
RAG typically assumes centralized access to documents, which breaks down when knowledge is distributed across private data silos. We propose a secure Federated RAG system built using Flower that performs local silo retrieval, while server-side aggregation and text generation run inside an attested, confidential compute environment, enabling confidential remote LLM inference even in the presence of honest-but-curious or compromised servers. We also propose a cascading inference approach that incorporates a non-confidential third-party model (e.g., Amazon Nova) as auxiliary context without weakening confidentiality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。