Adversarial Robustness in Financial Machine Learning: Defenses, Economic Impact, and Governance Evidence
By: Samruddhi Baviskar
Potential Business Impact:
Protects money-making computer programs from being tricked.
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.
Similar Papers
A unified Bayesian framework for adversarial robustness
Machine Learning (Stat)
Protects computer brains from sneaky tricks.
Conditional Adversarial Fragility in Financial Machine Learning under Macroeconomic Stress
Machine Learning (CS)
Makes money computers safer during tough times.
Adversarially-Aware Architecture Design for Robust Medical AI Systems
Machine Learning (CS)
Protects AI from tricks that harm patients.