To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding random noise. However, existing DPFL methods tend to make a sharper loss landscape and have poorer weight perturbation robustness, resulting in severe performance degradation. To alleviate these issues, we propose a novel DPFL algorithm named DP-FedSAM, which leverages gradient perturbation to mitigate the negative impact of DP. Specifically, DP-FedSAM integrates Sharpness Aware Minimization (SAM) optimizer to generate local flatness models with better stability and weight perturbation robustness, which results in the small norm of local updates and robustness to DP noise, thereby improving the performance. From the theoretical perspective, we analyze in detail how DP-FedSAM mitigates the performance degradation induced by DP. Meanwhile, we give rigorous privacy guarantees with R\'enyi DP and present the sensitivity analysis of local updates. At last, we empirically confirm that our algorithm achieves state-of-the-art (SOTA) performance compared with existing SOTA baselines in DPFL. Code is available at https://github.com/YMJS-Irfan/DP-FedSAM

翻译：为了抵御联邦学习中的推理攻击并缓解敏感信息泄露，客户端级差分隐私联邦学习（DPFL）通过裁剪局部更新并添加随机噪声，成为隐私保护的事实标准。然而，现有的DPFL方法往往使损失景观更加尖锐，并导致权重扰动鲁棒性较差，从而造成严重的性能下降。为缓解这些问题，我们提出了一种名为DP-FedSAM的新型DPFL算法，该算法利用梯度扰动来减轻差分隐私的负面影响。具体而言，DP-FedSAM集成了锐度感知最小化（SAM）优化器，以生成具有更好稳定性和权重扰动鲁棒性的局部平坦模型，这导致局部更新范数较小且对DP噪声具有鲁棒性，从而提升性能。从理论角度，我们详细分析了DP-FedSAM如何减轻由DP引起的性能下降。同时，我们利用Rényi差分隐私提供了严格的隐私保证，并给出了局部更新的敏感性分析。最后，我们通过实验证实，与现有DPFL中的最先进基线相比，我们的算法达到了最先进的性能。代码可在https://github.com/YMJS-Irfan/DP-FedSAM获取。