Adversarial Robustness in Financial Machine Learning: Defenses, Economic Impact, and Governance Evidence

Samruddhi Baviskar

Adversarial Robustness in Financial Machine Learning: Defenses, Economic Impact, and Governance Evidence

Machine Learning 2025-12-19 v1 Artificial Intelligence Cryptography and Security

Authors: Samruddhi Baviskar

Abstract

We evaluate adversarial robustness in tabular machine learning models used in financial decision making. Using credit scoring and fraud detection data, we apply gradient based attacks and measure impacts on discrimination, calibration, and financial risk metrics. Results show notable performance degradation under small perturbations and partial recovery through adversarial training.

Keywords

adversarial robustness financial machine learning credit scoring fraud detection adversarial training

Cite

@article{arxiv.2512.15780,
  title  = {Adversarial Robustness in Financial Machine Learning: Defenses, Economic Impact, and Governance Evidence},
  author = {Samruddhi Baviskar},
  journal= {arXiv preprint arXiv:2512.15780},
  year   = {2025}
}

Related papers

View all related →

Machine Learning · Statistics

Robust Classification of Financial Risk

Suproteem K. Sarkar, Kojin Oshiba, Daniel Giebisch, Yaron Singer