Conditional Adversarial Fragility in Financial Machine Learning under Macroeconomic Stress

TL;DR

This paper reveals that financial machine learning models are more vulnerable to adversarial attacks during macroeconomic stress periods, emphasizing the need for regime-aware robustness evaluation to ensure reliable decision-making in volatile economic conditions.

Contribution

It introduces a regime-aware evaluation framework for assessing adversarial robustness in financial models, highlighting the increased fragility during macroeconomic stress periods.

Findings

Models show similar performance across regimes under normal conditions.

Adversarial vulnerability significantly increases during stress periods.

False negative rates rise during macroeconomic stress under attack.

Abstract

Machine learning models used in financial decision systems operate in nonstationary economic environments, yet adversarial robustness is typically evaluated under static assumptions. This work introduces Conditional Adversarial Fragility, a regime dependent phenomenon in which adversarial vulnerability is systematically amplified during periods of macroeconomic stress. We propose a regime aware evaluation framework for time indexed tabular financial classification tasks that conditions robustness assessment on external indicators of economic stress. Using volatility based regime segmentation as a proxy for macroeconomic conditions, we evaluate model behavior across calm and stress periods while holding model architecture, attack methodology, and evaluation protocols constant. Baseline predictive performance remains comparable across regimes, indicating that economic stress alone does not induce inherent performance degradation. Under adversarial perturbations, however, models operating during stress regimes exhibit substantially greater degradation across predictive accuracy, operational decision thresholds, and risk sensitive outcomes. We further demonstrate that this amplification propagates to increased false negative rates, elevating the risk of missed high risk cases during adverse conditions. To complement numerical robustness metrics, we introduce an interpretive governance layer based on semantic auditing of model explanations using large language models. Together, these results demonstrate that adversarial robustness in financial machine learning is a regime dependent property and motivate stress aware approaches to model risk assessment in high stakes financial deployments.