Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detection
Authors:
- 14 October 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 126-133
Abstract
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 $O\left(n^{2}\right)$ 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 entity 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.
Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Large-scale Secure XGB for Vertical Federated Learning2021
- Research on Modeling of E-banking Fraud Account Identification Based on Federated Learning2021
- SecureBoost: A Lossless Federated Learning FrameworkIEEE Intelligent Systems, 2021
- Federated Machine LearningACM Transactions on Intelligent Systems and Technology, 2019
- Efficient Batched Oblivious PRF with Applications to Private Set Intersection2016
- XGBoost2016
- Local privacy and statistical minimax rates2013
- Privacy-preservation for gradient descent methods2007
- Foundations of Cryptography2004
- Public-Key Cryptosystems Based on Composite Degree Residuosity Classes1999