Fraud-RLA: A Reinforcement Learning Adversarial Attack Against Credit Card Fraud Detection
IEEE Transactions on Dependable and Secure Computing · 2026-05 · 23 (3) · 7468-7481
DOI: 10.1109/tdsc.2026.3673847 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, 2026-05. Verfasst von Daniele Lunghi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref). Gefördert von: DEDS project, EU Horizon Europe research and innovation programme DataGEMS.
Abstract (Originalsprache)
Adversarial attacks pose a significant threat to data-driven systems, and researchers have devoted considerable effort to studying them. Despite its economic relevance, credit card fraud detection has received comparatively little attention. To address this gap, we propose a novel threat model that highlights the limitations of existing attacks and motivates new approaches. We introduce Fraud-RLA, an adversarial attack against credit card Fraud Detection Systems that leverages Reinforcement Learning to evade detection. Fraud-RLA is designed to maximize the amount stolen by optimizing the exploration-exploitation trade-off while requiring substantially less prior knowledge than competing methods. Our experiments on a realistic Fraud Detection System show that Fraud-RLA is effective, even under the severe limitations imposed by our threat model.
Förderung
- DEDS project
- EU Horizon Europe research and innovation programme DataGEMS
Zitieren
APA
Lunghi, D., Molinghen, Y., Simitsis, A., Lenaerts, T., & Bontempi, G. (2026). Fraud-RLA: A Reinforcement Learning Adversarial Attack Against Credit Card Fraud Detection. IEEE Transactions on Dependable and Secure Computing, 23(3), 7468-7481. https://doi.org/10.1109/tdsc.2026.3673847
Vancouver
Lunghi D, Molinghen Y, Simitsis A, Lenaerts T, Bontempi G. Fraud-RLA: A Reinforcement Learning Adversarial Attack Against Credit Card Fraud Detection. IEEE Transactions on Dependable and Secure Computing. 2026;23(3):7468-7481. doi:10.1109/tdsc.2026.3673847
BibTeX
@article{Lunghi2026,
author = {Lunghi, Daniele and Molinghen, Yannick and Simitsis, Alkis and Lenaerts, Tom and Bontempi, Gianluca},
title = {Fraud-RLA: A Reinforcement Learning Adversarial Attack Against Credit Card Fraud Detection},
journal = {IEEE Transactions on Dependable and Secure Computing},
year = {2026},
volume = {23},
number = {3},
pages = {7468--7481},
doi = {10.1109/tdsc.2026.3673847}
}
EUVIMED