摘要联邦学习是由多个客户端协作开展模型训练的一种分布式机器学习解决方案.
在联邦学习架构下, 公平性被赋予了更加丰富的内涵: 一方面, 联邦学习中不同参与者对模型训练 …

Secure aggregation on user private data with the aid of an entrusted server provides strong
privacy guarantees and has been well-studied in the context of privacypreserving federated …

Federated learning (FL) is one of many tasks facilitated by crowdsourcing. Generally in such
a setting, participating workers cooperate to train a comprehensive model by exchanging the …

Federated Learning emerged as a promising solution to enable collaborative training
between organizations while avoiding centralization. However, it remains vulnerable to …

Most of the current federated learning schemes aimed at safeguarding privacy exhibit
vulnerability to collusion attacks and lack a verification mechanism for participants to …

Our work aims to minimize interaction in secure computation due to the high cost and
challenges associated with communication rounds, particularly in scenarios with many …

Recent secure aggregation protocols enable privacy-preserving federated learning for high-
dimensional models among thousands or even millions of participants. Due to the scale of …

Privacy-preserving federated learning (PPFL) is a paradigm of distributed privacypreserving
machine learning training in which a set of clients, each holding siloed training data, jointly …

This work introduces MicroSecAgg, a framework that addresses the intricacies of secure
aggregation in the single-server landscape, specifically tailored to situations where …

Distributed computing applications are booming in the Internet era as they enable mutually
distrusting parties to collaborate and achieve a common goal. One of the major challenges …