提出循环用户关联的分层安全聚合方案，提升通信与密钥生成效率。
Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Association
- 用户连接连续多个中继节点，实现跨集群编码通信。
- 结合梯度编码设计消息，支持高效聚合与安全密钥生成。
- 适用于大规模联邦学习中需保障中继隐私的场景。
安全聚合源于联邦学习（FL），旨在通过迭代通信过程，使云端服务器在满足数据安全要求的前提下，计算出众多客户端本地训练模型的聚合结果（即深度神经网络权重）。分层安全聚合（HSA）将该机制扩展至三层分层网络，其中用户通过中间层的中继节点与服务器通信。在HSA中，除服务器安全外，还需保证中继节点对用户输入完全无知（抽象为局部模型）。现有研究通常假设每个用户仅关联一个中继，限制了跨集群用户的编码机会，影响通信与密钥生成效率。本文提出一种基于循环关联模式的HSA方案，其中每个用户通过环形方式连接至连续的 $B$ 个中继节点。我们设计了一种受梯度编码启发的消息结构，并提出了高度非平凡的安全密钥生成机制，显著提升了系统性能。
原文摘要 · Abstract (English)
Secure aggregation is motivated by federated learning (FL) where a cloud server aims to compute an {aggregated} model (i.e., weights of deep neural networks) of the locally-trained models of numerous clients {through an iterative communication process}, while adhering to data security requirements. Hierarchical secure aggregation (HSA) extends this concept to a three-layer hierarchical network, where clustered users communicate with the server through an intermediate layer of relays. In HSA, beyond conventional server security, relay security is also enforced to ensure that the relays remain oblivious to the users' inputs (an abstraction of the local models in FL). {Existing studies on HSA that jointly consider communication and secret key generation efficiency typically assume that each user is associated with only one relay, limiting opportunities for coding across inter-cluster users to achieve efficient communication and key generation.} In this paper, we consider HSA with a cyclic association pattern where each user is connected to $B$ consecutive relays in a wrap-around manner. We propose an efficient aggregation scheme which includes a message design for the inputs inspired by gradient coding-a well-known technique for efficient communication in distributed computing-along with a highly non-trivial security key design.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。