Federated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However, malicious clients can perform poisoning attacks and model replacement to introduce backdoors into the trained global model. Although there have been intensive studies designing robust aggregation methods and empirical robust federated training protocols against backdoors, existing approaches lack robustness certification. This paper provides the first general framework, Certifiably Robust Federated Learning (CRFL), to train certifiably robust FL models against backdoors. Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude. Our certification also specifies the relation to federated learning parameters, such as poisoning ratio on instance level, number of attackers, and training iterations. Practically, we conduct comprehensive experiments across a range of federated datasets, and provide the first benchmark for certified robustness against backdoor attacks in federated learning. Our code is available at https://github.com/AI-secure/CRFL.

本论文提供了第一个通用框架，Certifiably Robust Federated Learning (CRFL)，用于训练具备抗击后门攻击认证的FL模型。该方法利用模型参数的裁剪和平滑来控制全局模型的平稳性，从而获得针对有限大小的后门的逐样本鲁棒性认证。同时，该认证还指明了联邦学习参数（如单个实例的攻击者比例，攻击者数量和训练迭代次数）之间的关系。

CRFL: 可验证抗后门攻击的联邦学习