Federated learning (FL) enables the training of models among distributed clients without compromising the privacy of training datasets, while the invisibility of clients datasets and the training process poses a variety of security threats. This survey provides the taxonomy of poisoning attacks and experimental evaluation to discuss the need for robust FL.

翻译：联邦学习(FL)在不损害培训数据集隐私的情况下,在分布式客户中进行模型培训,而客户数据集的隐蔽性和培训过程则造成各种安全威胁,该调查提供了中毒袭击分类和实验性评估,以讨论建立强有力的FL的必要性。