Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systems
Not on the map. Why?
Abstract (arXiv)
Global financial crime activity is driving demand for machine learning solutions in fraud prevention. However, prevention systems are commonly serviced to financial institutions in isolation, and few provisions exist for data sharing due to fears of unintentional leaks and adversarial attacks. Collaborative learning advances in finance are rare, and it is hard to find real-world insights derived from privacy-preserving data processing systems. In this paper, we present a collaborative deep learning framework for fraud prevention, designed from a privacy standpoint, and awarded at the recent PETs Prize Challenges. We leverage latent embedded representations of varied-length transaction sequences, along with local differential privacy, in order to construct a data release mechanism which can securely inform externally hosted fraud and anomaly detection models. We assess our contribution on two distributed data sets donated by large payment networks, and demonstrate robustness to popular inference-time attacks, along with utility-privacy trade-offs analogous to published work in alternative application domains.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 77 references that are in the map. First posted on arXiv 3 Jan 2024.
Builds on
25 of 77 references.
References · 25
- 2017Attention Is All You Needcited by 59,932
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
- 2017Deep Image Priorcited by 1,097
- 2019Deep Leakage from Gradientscited by 1,004
- 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
- 2019Towards Federated Learning at Scale: System Designcited by 826
- 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
- 2015Variational Dropout and the Local Reparameterization Trickcited by 489
- 2014Understanding Deep Image Representations by Inverting Themcited by 399
13 more
- 2020Information Leakage in Embedding Modelscited by 199
- 2018An efficient framework for learning sentence representationscited by 197
- 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
- 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 75
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
- 2018Privacy-preserving Neural Representations of Textcited by 54
- 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
- 2017Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learningcited by 34
- 2020CoLES: Contrastive Learning for Event Sequences with Self-Supervisioncited by 32
- 2020Asymmetrical Vertical Federated Learningcited by 26
- 2023Meet in the Middle: A New Pre-training Paradigmcited by 22
- 2020Interleaved Sequence RNNs for Fraud Detectioncited by 17
- 2021Attribution of Predictive Uncertainties in Classification Modelscited by 8
Built on by
Citing papers per year: 2026: 1.
1 paper.