测试金融模型对抗攻击下的鲁棒性，发现微小扰动导致性能下降。

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

• 用梯度攻击测试金融表格模型的抗干扰能力
• 微小扰动使模型准确率显著下降，部分通过对抗训练恢复
• 适合关注金融AI安全与治理的研究者

我们评估了用于金融决策的表格型机器学习模型在对抗攻击下的鲁棒性。基于信用评分和欺诈检测数据集，采用基于梯度的攻击方法，测量其对歧视性、校准性和金融风险指标的影响。结果显示，在微小扰动下模型性能出现明显下降，通过对抗训练可实现部分性能恢复。该研究揭示了金融机器学习模型在实际应用中的脆弱性及其潜在经济影响。

原文摘要 · Abstract (English)

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.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。