Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations by sharing training parameters instead of raw data. However, adversaries can still infer individual information through inference attacks (e.g. differential attacks) on these training parameters. As a result, Differential Privacy (DP) has been widely used in FL to prevent such attacks. We consider differentially private federated learning in a resource-constrained scenario, where both privacy budget and communication round are constrained. By theoretically analyzing the convergence, we can find the optimal number of differentially private local iterations for clients between any two sequential global updates. Based on this, we design an algorithm of differentially private federated learning with adaptive local iterations (ALI-DPFL). We experiment our algorithm on the FashionMNIST and CIFAR10 datasets, and demonstrate significantly better performances than previous work in the resource-constraint scenario.

翻译：联邦学习是一种分布式机器学习技术，允许在多个设备或组织之间通过共享训练参数（而非原始数据）进行模型训练。然而，攻击者仍可能通过针对这些训练参数的推理攻击（例如差分攻击）推断出个体信息。为此，差分隐私被广泛应用于联邦学习以防范此类攻击。本文研究资源受限场景下的差分隐私联邦学习，其中隐私预算和通信轮次均受到约束。通过理论分析收敛性，我们可在任意两次连续全局更新之间，为客户端确定最优的差分隐私本地迭代次数。基于此，我们设计了一种具有自适应本地迭代次数的差分隐私联邦学习算法（ALI-DPFL）。我们在FashionMNIST和CIFAR10数据集上进行了实验，证明在资源受限场景下该算法性能显著优于以往工作。