Federated Learning (FL) is a data-minimization approach enabling collaborative model training across diverse clients with local data, avoiding direct data exchange. However, state-of-the-art FL solutions to identify fraudulent financial transactions exhibit a subset of the following limitations. They (1) lack a formal security definition and proof, (2) assume prior freezing of suspicious customers' accounts by financial institutions (limiting the solutions' adoption), (3) scale poorly, involving either $O(n^2)$ computationally expensive modular exponentiation (where $n$ is the total number of financial institutions) or highly inefficient fully homomorphic encryption, (4) assume the parties have already completed the identity alignment phase, hence excluding it from the implementation, performance evaluation, and security analysis, and (5) struggle to resist clients' dropouts. This work introduces Starlit, a novel scalable privacy-preserving FL mechanism that overcomes these limitations. It has various applications, such as enhancing financial fraud detection, mitigating terrorism, and enhancing digital health. We implemented Starlit and conducted a thorough performance analysis using synthetic data from a key player in global financial transactions. The evaluation indicates Starlit's scalability, efficiency, and accuracy.

翻译：联邦学习是一种数据最小化方法，能够利用不同客户端的本地数据实现协作模型训练，同时避免直接数据交换。然而，当前用于识别欺诈性金融交易的最先进联邦学习解决方案存在以下部分局限性。它们：（1）缺乏正式的安全定义与证明；（2）假设金融机构事先冻结可疑客户账户（限制了方案的采用）；（3）扩展性差，涉及 $O(n^2)$ 计算代价高昂的模指数运算（其中 $n$ 为金融机构总数），或使用效率低下的全同态加密；（4）假设参与方已完成身份对齐阶段，因此未将其纳入实现、性能评估及安全性分析；（5）难以应对客户端退出问题。本研究提出Starlit，一种新颖的可扩展隐私保护联邦学习机制，克服了上述局限。该机制具有多种应用场景，例如增强金融欺诈检测、遏制恐怖主义及推动数字健康。我们实现了Starlit，并利用全球金融交易领域关键参与者的合成数据进行了全面性能分析。评估结果表明了Starlit的可扩展性、效率及准确性。