Black-Box Attack-Based Security Evaluation Framework for Credit Card Fraud Detection Models

Jin Xiao (), Yuhang Tian (), Yanlin Jia (), Xiaoyi Jiang (), Lean Yu () and Shouyang Wang ()
Additional contact information
Jin Xiao: Business School, Sichuan University, Chengdu 610064, China
Yuhang Tian: Business School, Sichuan University, Chengdu 610064, China
Yanlin Jia: School of Sciences, Southwest Petroleum University, Chengdu 610500, China
Xiaoyi Jiang: Faculty of Mathematics and Computer Science, University of Münster, Münster D-48149, Germany
Lean Yu: Business School, Sichuan University, Chengdu 610064, China
Shouyang Wang: School of Entrepreneurship and Management, ShanghaiTech University, Shanghai 201210, China

INFORMS Journal on Computing, 2023, vol. 35, issue 5, 986-1001

Abstract: The security of credit card fraud detection (CCFD) models based on machine learning is important but rarely considered in the existing research. To this end, we propose a black-box attack-based security evaluation framework for CCFD models. Under this framework, the semisupervised learning technique and transfer-based black-box attack are combined to construct two versions of a semisupervised transfer black-box attack algorithm. Moreover, we introduce a new nonlinear optimization model to generate the adversarial examples against CCFD models and a security evaluation index to quantitatively evaluate the security of them. Computing experiments on two real data sets demonstrate that, facing the adversarial examples generated by the proposed attack algorithms, all six supervised models considered largely lose their ability to identify the fraudulent transactions, whereas the two unsupervised models are less affected. This indicates that the CCFD models based on supervised machine learning may possess substantial security risks. In addition, the evaluation results for the security of the models generate important managerial implications that help banks reasonably evaluate and enhance the model security.

Keywords: nonlinear optimization; credit card fraud detection models; security evaluation; black-box attack; adversarial examples; machine learning (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/ijoc.2023.1297 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orijoc:v:35:y:2023:i:5:p:986-1001

Access Statistics for this article

More articles in INFORMS Journal on Computing from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().