The majority of work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can train complete models independently. However, in many interesting problems, such as financial fraud detection and disease detection, individual data points are scattered across different clients/organizations in vertical federated learning. Solutions for this type of FL require the exchange of gradients between participants and rarely consider privacy and security concerns, posing a potential risk of privacy leakage. In this work, we present a novel design for training vertical FL securely and efficiently using state-of-the-art security modules for secure aggregation. We demonstrate empirically that our method does not impact training performance whilst obtaining 9.1e2 ~3.8e4 speedup compared to homomorphic encryption (HE).

翻译：大多数关于隐私保护联邦学习（FL）的研究工作集中在水平划分的数据集上，即客户端共享相同的特征集，并且能够独立训练完整的模型。然而，在许多有趣的问题中，例如金融欺诈检测和疾病检测，垂直联邦学习中的个体数据点分散在不同的客户端/组织之间。这种类型的FL解决方案需要在参与者之间交换梯度，但很少考虑隐私和安全问题，从而带来隐私泄露的潜在风险。在本工作中，我们提出了一种新颖的设计，利用最先进的安全聚合安全模块，安全且高效地训练垂直联邦学习。我们通过实验证明，我们的方法在获得9.1e2~3.8e4倍加速比（相较于同态加密（HE））的同时，不会影响训练性能。