Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits

Computer Science > Cryptography and Security [Submitted on 8 Aug 2026] Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma Selective-risk certificates promise that accepted outputs meet a declared error target. We develop Fed-SRC, a score-agnostic certificate for federated, differentially private, adaptively monitored retrieval-augmented generation. Clients release only Gaussian-perturbed score and loss histograms. Record-indexed and noise-variance-indexed martingales jointly bound target-risk contrast and accepted mass over all registered thresholds and rounds, permitting predictable recruitment, dropout, threshold selection, and optional stopping. A range-one total-variation term transfers the calibration mixture to a declared deployment mixture. The contribution is this private, federated, anytime combination, rather than the contrast statistic or acceptance floor individually. Empirically, no simultaneous-bound violation occurs in any evaluated cell, privacy level, or policy. Operational power depends on the score and population: the primary target r*=0.10 never certifies, and on RAGTruth the secondary target r*=0.20 never certifies either, whereas on HaluEval question answering it certifies in all 200 non-private trials, with held-out risk below the target. Naively privatized non-private certificates violate their bounds in 146 to 198 of 200 trials. As an exploratory comparison, we also evaluate a private betting-capital heuristic for which we do not establish e-process validity. This heuristic stops certifying at epsilon <= 4, where Fed-SRC still certifies. Certification nevertheless consumes roughly 30 times more stream events than unique calibration items. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2608.07913 [cs.CR]   (or arXiv:2608.07913v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.07913 Focus to learn more Submission history From: Ibne Farabi Shihab [view email] [v1] Sat, 8 Aug 2026 04:38:35 UTC (76 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.AI 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?)