Supercharging Federated Intelligence Retrieval
This addresses the challenge of secure knowledge retrieval in federated settings for applications like healthcare or finance, though it is incremental as it builds on existing federated learning and RAG methods.
The paper tackles the problem of performing retrieval-augmented generation (RAG) when knowledge is distributed across private data silos by proposing a secure Federated RAG system that enables confidential remote LLM inference, achieving results such as maintaining confidentiality even with honest-but-curious or compromised servers.
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.