The past four years have witnessed the rapid development of federated learning (FL). However, new privacy concerns have also emerged during the aggregation of the distributed intermediate results. The emerging privacy-preserving FL (PPFL) has been heralded as a solution to generic privacy-preserving machine learning. However, the challenge of protecting data privacy while maintaining the data utility through machine learning still remains. In this article, we present a comprehensive and systematic survey on the PPFL based on our proposed 5W-scenario-based taxonomy. We analyze the privacy leakage risks in the FL from five aspects, summarize existing methods, and identify future research directions.

中文翻译：

---

隐私保护联邦学习的综合调查

过去四年见证了联邦学习（FL）的快速发展。然而，在分布式中间结果的聚合过程中也出现了新的隐私问题。新兴的隐私保护 FL (PPFL) 被誉为通用隐私保护机器学习的解决方案。然而，在通过机器学习维护数据实用性的同时保护数据隐私的挑战仍然存在。在本文中，我们基于我们提出的基于 5W 场景的分类法，对 PPFL 进行了全面而系统的调查。我们从五个方面分析了 FL 中的隐私泄露风险，总结了现有的方法，并确定了未来的研究方向。