mlsanityData to 7 Oct 2026

Supercharging Federated Intelligence Retrieval

arXiv 2603.25374 ↗First posted 26 Mar 2026cs.IR cs.CL cs.CRcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 26 Mar 2026.

Builds on

13 of 20 references.

References · 13

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  4. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  5. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  6. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 326
  7. 2024C-FedRAG: A Confidential Federated Retrieval-Augmented Generation Systemcited by 19
  8. 2018SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Executioncited by 13
  9. 2024FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generationcited by 12
  10. 2025Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generationcited by 7
  11. 2025Federated Retrieval-Augmented Generation: A Systematic Mapping Studycited by 5
  12. 2024Federated Learning and RAG Integration: A Scalable Approach for Medical Large Language Modelscited by 4
1 more
  1. 2020SOTERIA: In Search of Efficient Neural Networks for Private Inferencecited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG
  2. 2026FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters
  3. 2025HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Data
  4. 2026Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction
  5. 2026FD-RAG: Federated Dual-System Retrieval-Augmented Generation
  6. 2024RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
  7. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
  8. 2026P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval