Convergent Differential Privacy Analysis for General Federated Learning

ICLR 2026 Conference Submission19935 Authors

Keywords: Differential privacy, federated learning

TL;DR: We analyze the convergent differential privacy bound for the worst case in the general federated learning.

Abstract:

The powerful cooperation of federated learning (FL) and differential privacy (DP) provides a promising paradigm for the large-scale private clients. However, existing analyses in FL-DP mostly rely on the composition theorem and cannot tightly quantify the privacy leakage challenges, which is tight for a few communication rounds but yields an arbitrarily loose and divergent bound eventually. This also implies a counterintuitive judgment, suggesting that FL-DP may not provide adequate privacy support during long-term training under constant-level noisy perturbations, yielding discrepancy between the theoretical and experimental results. To further investigate the convergent privacy and reliability of the FL-DP framework, in this paper, we comprehensively evaluate the worst privacy of two classical methods under the non-convex and smooth objectives based on the $f$-DP analysis. With the aid of the shifted interpolation technique, we successfully prove that privacy in Noisy-FedAvg has a tight convergent bound. Moreover, with the regularization of the proxy term, privacy in Noisy-FedProx has a stable constant lower bound. Our analysis further demonstrates a solid theoretical foundation for the reliability of privacy in FL-DP. Meanwhile, our conclusions can also be losslessly converted to other classical DP analytical frameworks, e.g.
$(\epsilon,\delta)$-DP and R$\'{e}$nyi-DP (RDP), to provide more fine-grained understandings for the FL-DP frameworks.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 19935