# Supercharging Federated Intelligence Retrieval

arXiv: https://arxiv.org/abs/2603.25374 · HTML: https://mlsanity.com/paper/2603.25374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 13 of 13)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System](https://mlsanity.com/paper/2412.13163/) (2024)
- [SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Execution](https://mlsanity.com/paper/1802.09085/) (2018)
- [FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.13272/) (2024)
- [Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.19101/) (2025)
- [Federated Retrieval-Augmented Generation: A Systematic Mapping Study](https://mlsanity.com/paper/2505.18906/) (2025)
- [Federated Learning and RAG Integration: A Scalable Approach for Medical Large Language Models](https://mlsanity.com/paper/2412.13720/) (2024)
- [SOTERIA: In Search of Efficient Neural Networks for Private Inference](https://mlsanity.com/paper/2007.12934/) (2020)

## Abstract (arXiv)

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.