Adversarial Robustness in Financial Machine Learning: Defenses, Economic Impact, and Governance Evidence
This addresses security vulnerabilities in financial decision-making systems, but it is incremental as it applies known methods to a specific domain.
The study assessed adversarial robustness in financial machine learning models, finding that small perturbations cause significant performance degradation in credit scoring and fraud detection, with adversarial training providing only partial recovery.
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.