Conditional Adversarial Fragility in Financial Machine Learning under Macroeconomic Stress

• URL: http://arxiv.org/abs/2512.19935v1
• Date: Mon, 22 Dec 2025 23:44:39 GMT
• Title: Conditional Adversarial Fragility in Financial Machine Learning under Macroeconomic Stress
• Authors: Samruddhi Baviskar,
• Abstract summary: Adversarial Fragility is a regime dependent phenomenon in which adversarial vulnerability is systematically amplified during periods of macroeconomic stress.<n>We show 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Machine Learning Enabled Early Warning System For Financial Distress Using Real-Time Digital Signals [0.07282038457285603]
  This study introduces a machine learning-based early warning system to identify financial distress in near real-time.<n>We use a panel dataset of 750 households tracked over three monitoring rounds spanning 13 months.<n>System performs reliably for both binary distress detection and multi-class severity classification.
  arXiv  Detail & Related papers  (2025-10-25T13:12:45Z)
• Are Large Reasoning Models Interruptible? [77.53059044071107]
  Large Reasoning Models (LRMs) excel at complex reasoning but are traditionally evaluated in static, "frozen world" settings.<n>We show that even state-of-the-art LRMs, which achieve high accuracy in static settings, can fail unpredictably when interrupted or exposed to changing context.<n>Our analysis further reveals several novel failure modes, including reasoning leakage, panic, and self-doubt.
  arXiv  Detail & Related papers  (2025-10-13T17:59:35Z)
• Uncertainty Quantification for Regression using Proper Scoring Rules [76.24649098854219]
  We introduce a unified UQ framework for regression based on proper scoring rules, such as CRPS, logarithmic, squared error, and quadratic scores.<n>We derive closed-form expressions for the uncertainty measures under practical parametric assumptions and show how to estimate them using ensembles of models.<n>Our broad evaluation on synthetic and real-world regression datasets provides guidance for selecting reliable UQ measures.
  arXiv  Detail & Related papers  (2025-09-30T17:52:12Z)
• Methodological Insights into Structural Causal Modelling and Uncertainty-Aware Forecasting for Economic Indicators [4.9930207509018425]
  We focus on four key U.S. macroeconomic indicators -- GDP, economic growth, inflation, and unemployment.<n>Our results reveal a robust unidirectional causal link from economic growth to GDP.<n>We use a large language model trained for time series to perform zero-shot predictions on unemployment.
  arXiv  Detail & Related papers  (2025-09-08T04:52:12Z)
• FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making [58.04602111184477]
  FinHEAR is a framework for Human Expertise and Adaptive Risk-aware reasoning.<n>It orchestrates specialized agents to analyze historical trends, interpret current events, and retrieve expert-informed precedents.<n> Empirical results on financial datasets show that FinHEAR consistently outperforms strong baselines across trend prediction and trading tasks.
  arXiv  Detail & Related papers  (2025-06-10T04:06:51Z)
• Modeling Regime Structure and Informational Drivers of Stock Market Volatility via the Financial Chaos Index [0.0]
  This paper investigates the structural dynamics of stock market volatility through the Financial Chaos Index.<n>We identify three distinct market regimes, low-chaos, intermediate-chaos, and high-chaos, each characterized by differing levels of systemic stress.<n>We find that shifts in macroeconomic, financial, policy, and geopolitical uncertainty exhibit strong predictive power for volatility dynamics across regimes.
  arXiv  Detail & Related papers  (2025-04-26T15:48:11Z)
• Hamiltonian Neural Networks for Robust Out-of-Time Credit Scoring [0.5439020425819]
  This paper presents a novel credit scoring approach using neural networks to address class imbalance and out-of-time prediction challenges.<n>We develop a specific and loss function inspired by Hamiltonian mechanics that better captures credit risk dynamics.
  arXiv  Detail & Related papers  (2024-10-14T06:08:26Z)
• Forecasting and stabilizing chaotic regimes in two macroeconomic models via artificial intelligence technologies and control methods [0.3670422696827526]
  One of the key tasks in the economy is forecasting the economic agents' expectations of the future values of economic variables. The behavior of mathematical models can be irregular, including chaotic, which reduces their predictive power. We study the regimes of behavior of two economic models and identify irregular dynamics in them.
  arXiv  Detail & Related papers  (2023-02-20T11:55:15Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• Bayesian Bilinear Neural Network for Predicting the Mid-price Dynamics in Limit-Order Book Markets [84.90242084523565]
  Traditional time-series econometric methods often appear incapable of capturing the true complexity of the multi-level interactions driving the price dynamics. By adopting a state-of-the-art second-order optimization algorithm, we train a Bayesian bilinear neural network with temporal attention. By addressing the use of predictive distributions to analyze errors and uncertainties associated with the estimated parameters and model forecasts, we thoroughly compare our Bayesian model with traditional ML alternatives.
  arXiv  Detail & Related papers  (2022-03-07T18:59:54Z)
• Stateful Offline Contextual Policy Evaluation and Learning [88.9134799076718]
  We study off-policy evaluation and learning from sequential data. We formalize the relevant causal structure of problems such as dynamic personalized pricing. We show improved out-of-sample policy performance in this class of relevant problems.
  arXiv  Detail & Related papers  (2021-10-19T16:15:56Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.