Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations without sharing data. However, while FL ensures that the raw data is not directly accessible to external adversaries, adversaries can still obtain some statistical information about the data through differential attacks. Differential Privacy (DP) has been proposed, which adds noise to the model or gradients to prevent adversaries from inferring private information from the transmitted parameters. We reconsider the framework of differential privacy federated learning in resource-constrained scenarios (privacy budget and communication resources). We analyze the convergence of federated learning with differential privacy (DPFL) on resource-constrained scenarios and propose an Adaptive Local Steps Differential Privacy Federated Learning (ALS-DPFL) algorithm. We experiment our algorithm on the FashionMNIST and Cifar-10 datasets and achieve quite good performance relative to previous work.

翻译：联邦学习（FL）是一种分布式机器学习技术，允许多个设备或组织在不共享数据的情况下进行模型训练。然而，虽然联邦学习确保原始数据不会被外部攻击者直接获取，但攻击者仍可通过差分攻击获取数据的部分统计信息。为此，研究人员提出了差分隐私（DP）技术，通过在模型或梯度中添加噪声，防止攻击者从传输参数中推断出私有信息。我们重新审视了资源受限场景（隐私预算和通信资源）下的差分隐私联邦学习框架。我们分析了资源受限场景中差分隐私联邦学习（DPFL）的收敛性，并提出了一种自适应本地步长差分隐私联邦学习（ALS-DPFL）算法。我们在FashionMNIST和Cifar-10数据集上对算法进行了实验，相较于先前工作取得了相当出色的性能。