Differential privacy (DP) is crucial for safeguarding sensitive client information in federated learning (FL), yet traditional DP-FL methods rely predominantly on fixed gradient clipping thresholds. Such static clipping neglects significant client heterogeneity and varying privacy sensitivities, which may lead to an unfavorable privacy-utility trade-off. In this paper, we propose PAC-DP, a Personalized Adaptive Clipping framework for federated learning under record-level local differential privacy. PAC-DP introduces a Simulation-CurveFitting approach leveraging a server-hosted public proxy dataset to learn an effective mapping between personalized privacy budgets epsilon and gradient clipping thresholds C, which is then deployed online with a lightweight round-wise schedule. This design enables budget-conditioned threshold selection while avoiding data-dependent tuning during training. We provide theoretical analyses establishing convergence guarantees under the per-example clipping and Gaussian perturbation mechanism and a reproducible privacy accounting procedure. Extensive evaluations on multiple FL benchmarks show that PAC-DP surpasses conventional fixed-threshold approaches under matched privacy budgets, improving accuracy by up to 26% and accelerating convergence by up to 45.5% in our evaluated settings.

翻译：差分隐私（DP）对于保护联邦学习（FL）中敏感客户端信息至关重要，但传统DP-FL方法主要依赖固定梯度裁剪阈值。这种静态裁剪忽略了显著的客户端异质性和不同的隐私敏感性，可能导致隐私-效用权衡不理想。本文提出PAC-DP，一种基于记录级本地差分隐私的联邦学习个性化自适应裁剪框架。PAC-DP引入模拟-曲线拟合方法，利用服务器托管的公共代理数据集学习个性化隐私预算ε与梯度裁剪阈值C之间的有效映射，随后通过轻量级逐轮调度方案在线部署。该设计实现了预算条件化的阈值选择，同时避免了训练过程中依赖于数据的调整。我们提供了理论分析，在逐样本裁剪和高斯扰动机制下建立了收敛保证，并给出了可复现的隐私核算流程。在多个FL基准上的广泛评估表明，在匹配隐私预算下，PAC-DP优于传统固定阈值方法，在所评估设置中准确率提升最高达26%，收敛速度加快最高达45.5%。