提出隐私保护的垂直联邦学习框架，支持多方安全计算与差分隐私。
Secure and Privacy-Preserving Vertical Federated Learning
- 拆分聚合角色，用多方安全计算实现模型与特征聚合。
- 相比传统方案，计算和通信开销大幅降低，支持全局与局部模型更新。
- 适合数据不共享的多方协作场景，如金融、医疗联合建模。
我们提出一种新型端到端隐私保护框架，针对垂直联邦学习中特征跨客户端划分、标签不共享的场景，设计三种高效协议以适配不同部署需求，同时保障输入与输出隐私。通过将联邦学习中的聚合器角色分散至多个服务器，并由其运行安全多方计算（MPC）协议完成模型与特征聚合，同时对最终发布的模型应用差分隐私（DP）。与直接将训练全量迁移至服务器间进行MPC的朴素方案相比，我们的优化方案支持纯全局及全局-局部模型更新，在保障隐私的同时显著减少多方计算的计算与通信开销。实验结果验证了所提协议的有效性。
原文摘要 · Abstract (English)
We propose a novel end-to-end privacy-preserving framework, instantiated by three efficient protocols for different deployment scenarios, covering both input and output privacy, for the vertically split scenario in federated learning (FL), where features are split across clients and labels are not shared by all parties. We do so by distributing the role of the aggregator in FL into multiple servers and having them run secure multiparty computation (MPC) protocols to perform model and feature aggregation and apply differential privacy (DP) to the final released model. While a naive solution would have the clients delegating the entirety of training to run in MPC between the servers, our optimized solution, which supports purely global and also global-local models updates with privacy-preserving, drastically reduces the amount of computation and communication performed using multiparty computation. The experimental results also show the effectiveness of our protocols.
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。