Federated learning (FL) is a promising approach that allows many clients to jointly train a model without sharing the raw data. Due to the clients' different preferences, the class imbalance issue frequently occurs in real-world FL problems and poses threats for poisoning attacks to the existing FL methods. In this work, we first propose a new attack called Class Imbalance Attack that can degrade the testing accuracy of a particular class(es) to even 0 under the state-of-the-art robust FL methods. To defend against such attacks, we further propose a Class-Balanced FL method with a novel contribution-wise Byzantine-robust aggregation rule. In the designed rule, an honest score and a contribution score will be assigned to each client dynamically according to the server model. The server itself will be initiated with a small dataset, and a model (called server model) will be maintained. These two scores will be subsequently used to calculate the weighted average of the client gradients for each training iteration. The experiments are conducted on five datasets against state-of-the-art poisoning attacks, including the Class Imbalance Attack. The empirical results demonstrate the effectiveness of the proposed Class-Balanced FL method.

中文翻译：

---

用于类平衡联邦学习的贡献型拜占庭鲁棒聚合

联邦学习（FL）是一种很有前途的方法，它允许许多客户在不共享原始数据的情况下联合训练模型。由于客户的偏好不同，类不平衡问题在现实世界的 FL 问题中经常出现，并对现有 FL 方法造成中毒攻击的威胁。在这项工作中，我们首先提出了一种称为类不平衡攻击的新攻击，它可以在最先进的鲁棒 FL 方法下将特定类的测试精度降低到甚至 0。为了防御此类攻击，我们进一步提出了一种类平衡 FL 方法，该方法具有新颖的贡献智能拜占庭鲁棒聚合规则。在设计的规则中，将根据服务器模型动态地为每个客户端分配诚实分数和贡献分数。服务器本身将使用一个小数据集启动，并维护一个模型（称为服务器模型）。这两个分数随后将用于计算每次训练迭代的客户端梯度的加权平均值。这些实验是在五个数据集上进行的，针对最先进的中毒攻击，包括类不平衡攻击。实证结果证明了所提出的类平衡 FL 方法的有效性。