提出新型隐私保护联邦学习框架，兼顾通信效率与数据安全。
PBM-VFL: Vertical Federated Learning with Feature and Sample Privacy
- 结合泊松二项机制与安全多方计算，实现特征与样本隐私保护。
- 首次建立差分隐私预算、收敛误差与通信开销的理论关系。
- 实测在高隐私保障下仍保持良好模型性能，适合医疗金融场景。
我们提出泊松二项机制垂直联邦学习（PBM-VFL），一种具备差分隐私保证且通信高效的垂直联邦学习算法。PBM-VFL 将安全多方计算与近期提出的泊松二项机制相结合，在模型训练过程中保护各参与方的私有数据集。我们定义了新的特征隐私概念，并分析了算法端到端的特征与样本隐私。我们对比了垂直联邦学习与水平联邦学习中的样本隐私损失。此外，我们首次提供了不同差分隐私条件下隐私预算、收敛误差与通信成本之间关系的理论刻画。最后，实验表明我们的模型在高隐私水平下仍能保持良好性能。
原文摘要 · Abstract (English)
We present Poisson Binomial Mechanism Vertical Federated Learning (PBM-VFL), a communication-efficient Vertical Federated Learning algorithm with Differential Privacy guarantees. PBM-VFL combines Secure Multi-Party Computation with the recently introduced Poisson Binomial Mechanism to protect parties' private datasets during model training. We define the novel concept of feature privacy and analyze end-to-end feature and sample privacy of our algorithm. We compare sample privacy loss in VFL with privacy loss in HFL. We also provide the first theoretical characterization of the relationship between privacy budget, convergence error, and communication cost in differentially-private VFL. Finally, we empirically show that our model performs well with high levels of privacy.
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。