Federated Learning has emerged as a dominant computational paradigm for distributed machine learning. Its unique data privacy properties allow us to collaboratively train models while offering participating clients certain privacy-preserving guarantees. However, in real-world applications, a federated environment may consist of a mixture of benevolent and malicious clients, with the latter aiming to corrupt and degrade federated model's performance. Different corruption schemes may be applied such as model poisoning and data corruption. Here, we focus on the latter, the susceptibility of federated learning to various data corruption attacks. We show that the standard global aggregation scheme of local weights is inefficient in the presence of corrupted clients. To mitigate this problem, we propose a class of task-oriented performance-based methods computed over a distributed validation dataset with the goal to detect and mitigate corrupted clients. Specifically, we construct a robust weight aggregation scheme based on geometric mean and demonstrate its effectiveness under random label shuffling and targeted label flipping attacks.

翻译：联邦学习联盟已成为分布式机器学习的主要计算模式。它独特的数据隐私特性使我们能够合作培训模型,同时向参与的客户提供某些隐私保护保障。然而,在现实应用中,联合环境可能由慈善和恶意的客户混合组成,后者的目的是腐蚀和削弱联邦模式的绩效。不同的腐败计划,例如模式中毒和数据腐败,可以适用不同的腐败计划。我们在这里关注后者,即联合学习容易受到各种数据腐败袭击。我们显示,当腐败客户出现时,当地加权标准全球汇总计划效率低下。为了缓解这一问题,我们建议了一组基于任务的基于绩效的方法,对分布式验证数据集进行计算,目的是检测和减轻腐败客户的绩效。具体地说,我们根据几何平均值构建一个强力的权重汇总计划,并在随机标签打乱和有针对性的标签翻动攻击下展示其有效性。