Challenges and future directions of secure federated learning: a survey
作者:Zhang, Kaiyue;Song, Xuan;Zhang, Chenhan;Yu, Shui
期刊:(2021) Engineering Applications of Artificial Intelligence
Abstract:Federated learning came into being with the increasing concern of privacy security, as people’s sensitive information is being exposed under the era of big data. It is an algorithm that does not collect users’ raw data, but aggregates model parameters from each client and therefore protects user’s privacy. Nonetheless, due to the inherent distributed nature of federated learning, it is more vulnerable under attacks since users may upload malicious data to break down the federated learning server. In addition, some recent studies have shown that attackers can recover information merely from parameters. Hence, there is still lots of room to improve the current federated learning frameworks. In this survey, we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated learning. Several open issues and existing solutions in federated learning are discussed. We also point out the future research directions of federated learning.
Keyword: federated learning, privacy protection, security
摘要: 随着大数据时代下人们的敏感信息被暴露，联邦学习伴随着隐私安全的日益关注应运而生。它是一种不收集用户原始数据，而是从每个客户端聚合模型参数从而保护用户隐私的算法。然而，由于联邦学习固有的分布式特性，用户可能会上传恶意数据来破坏联邦学习服务器，使得联邦学习在遭受攻击时更加脆弱。此外，最近的一些研究表明，攻击者可以仅从参数中恢复信息。因此，目前的联邦学习框架还有很大的改进空间。在这篇综述中，我们简要回顾了联邦学习的最新技术，并详细讨论了联邦学习的改进。讨论了联邦学习中的几个开放性问题和现有的解决方法。我们还指出了联邦学习未来的研究方向。
关键字:联邦学习,隐私保护,安全
DOI:10.1007/s11704-021-0598-z
全文链接:https://link.springer.com/content/pdf/10.1007/s11704-021-0598-z.pdf?pdf=button
注意：欢迎转载，转载时请注明来源
