Adversarial Robustness of Credit Scoring Models - Leveraging GANs for Model Evaluation and Security

Adarsh Naidu

doi:10.36948/ijfmr.2019.v01i01.40956

Adversarial Robustness of Credit Scoring Models - Leveraging GANs for Model Evaluation and Security

Author(s)	Adarsh Naidu
Country	United States
Abstract	Credit scoring models play a crucial role in the financial industry by enabling lenders to assess creditworthiness efficiently. However, these machine learning-based models are susceptible to adversarial attacks, where fraudulent actors manipulate input data to trick the system into approving high-risk applicants. This study explores the application of Generative Adversarial Networks (GANs) in generating synthetic adversarial examples to evaluate the robustness of credit scoring models. By training GANs on historical credit data, we generate realistic adversarial samples that expose vulnerabilities in existing models. Experimental results demonstrate that these GAN-generated adversarial instances successfully mislead a standard credit scoring model in 25% of cases. To counteract this issue, we propose adversarial training as a defense mechanism, reducing the misclassification rate to 10%, thereby strengthening model resilience. This research highlights the importance of adversarial robustness in credit scoring models and introduces a novel framework for assessing and enhancing their security. The findings contribute to improving the reliability of credit decision-making while addressing regulatory compliance and fraud prevention challenges in the financial sector. Future research will focus on exploring advanced GAN architectures and establishing standardized benchmarks for robustness assessment.
Field	Engineering
Published In	Volume 1, Issue 1, July-August 2019
Published On	2019-07-05
DOI	https://doi.org/10.36948/ijfmr.2019.v01i01.40956
Short DOI	https://doi.org/g9dgm9

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 2 Cover Page Vol 7 Isu 1 Cover Page Vol 6 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Adversarial Robustness of Credit Scoring Models - Leveraging GANs for Model Evaluation and Security

Share this