Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detection
Authors:
- Aydin AbadiAAAydin Abadi
- Bradley DoyleBDBradley Doyle
- Kieron GuinamardKGKieron Guinamard
- Sasi Kumar MurakondaSMSasi Kumar Murakonda
- Jack LiddellJLJack Liddell
- Steven J. MurdochSMSteven J. Murdoch
- Mohammad NaseriMNMohammad Naseri
- George TheodorakopoulosGTGeorge Theodorakopoulos
- Suzanne WellerSWSuzanne Weller
Preprint
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 $O(n^2)$ 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.
Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Smartwatches in healthcare medicine: assistance and monitoring; a scoping reviewBMC Medical Informatics and Decision Making, 2023
- ${\sf FederBoost}$: Private Federated Learning for GBDTIEEE Transactions on Dependable and Secure Computing, 2023
- An Analysis on Financial Statement Fraud Detection for Chinese Listed Companies Using Deep LearningIEEE Access, 2022
- AI in Finance: Challenges, Techniques, and OpportunitiesACM Computing Surveys, 2022
- An Extensive Formal Analysis of Multi-factor Authentication ProtocolsACM Transactions on Privacy and Security, 2021
- A survey on multi-factor authentication for online banking in the wildComputers & Security, 2020
- FFD: A Federated Learning Based Method for Credit Card Fraud Detection2019
- Efficient Batched Oblivious PRF with Applications to Private Set Intersection2016
- Improved OT Extension for Transferring Short Secrets2013
- Public-Key Cryptosystems Based on Composite Degree Residuosity Classes1999