Federated learning (FL) is an advanced distributed machine learning method that effectively solves the data silo problem. With the increasing popularity of federated learning and the growing importance of privacy protection, federated learning methods that can securely aggregate models have received widespread attention. Federated learning enables clients to train models locally and share their model updates with the server. While this approach allows collaborative model training without exposing raw data, it still risks leaking sensitive information. To enhance privacy protection in federated learning, secure aggregation is considered a key enabling technology that requires further in-depth investigation. This paper summarizes the definition, classification, and applications of federated learning; reviews secure aggregation protocols proposed to address privacy and security issues in federated learning; extensively analyzes the selected protocols; and concludes by highlighting the significant challenges and future research directions in applying secure aggregation in federated learning. The purpose of this paper is to review and analyze prior research, evaluate the advantages and disadvantages of various secure aggregation schemes, and propose potential future research directions. This work aims to serve as a valuable reference for researchers studying secure aggregation in federated learning.
Zhang et al. (Thu,) studied this question.