← Back ◬ AI & Machine Learning Mar 27, 2026

Supercharging Federated Intelligence Retrieval

arXiv Security Archived Mar 27, 2026 ✓ Full text saved

arXiv:2603.25374v1 Announce Type: cross Abstract: 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 als

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Information Retrieval [Submitted on 26 Mar 2026] Supercharging Federated Intelligence Retrieval Dimitris Stripelis, Patrick Foley, Mohammad Naseri, William Lindskog-Münzing, Chong Shen Ng, Daniel Janes Beutel, Nicholas D. Lane 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. Comments: 6 pages, 1 figure, 2 tables Subjects: Information Retrieval (cs.IR); Computation and Language (cs.CL); Cryptography and Security (cs.CR); Machine Learning (cs.LG) MSC classes: 68P20, 68T05, 62M45, 68P25, 68T50, 68T10 ACM classes: H.3.3; I.2.7 Cite as: arXiv:2603.25374 [cs.IR] (or arXiv:2603.25374v1 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2603.25374 Focus to learn more Submission history From: Dimitris Stripelis [view email] [v1] Thu, 26 Mar 2026 12:23:53 UTC (123 KB) Access Paper: HTML (experimental) view license Current browse context: cs.IR < prev | next > new | recent | 2026-03 Change to browse by: cs cs.CL cs.CR cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes