Distributional Adversarial Attacks and Training in Deep Hedging

TL;DR

This paper investigates the vulnerability of deep hedging strategies to distributional shifts and introduces an adversarial training framework using Wasserstein balls to enhance their robustness against market uncertainties.

Contribution

It extends adversarial attacks to the distributional setting and proposes a computationally efficient training method for more resilient deep hedging strategies.

Findings

Adversarially trained strategies outperform classical models in out-of-sample tests.

Robust strategies maintain performance during market changes.

Training over Wasserstein balls improves resilience to distributional shifts.

Abstract

In this paper, we study the robustness of classical deep hedging strategies under distributional shifts by leveraging the concept of adversarial attacks. We first demonstrate that standard deep hedging models are highly vulnerable to small perturbations in the input distribution, resulting in significant performance degradation. Motivated by this, we propose an adversarial training framework tailored to increase the robustness of deep hedging strategies. Our approach extends pointwise adversarial attacks to the distributional setting and introduces a computationally tractable reformulation of the adversarial optimization problem over a Wasserstein ball. This enables the efficient training of hedging strategies that are resilient to distributional perturbations. Through extensive numerical experiments, we show that adversarially trained deep hedging strategies consistently outperform their classical counterparts in terms of out-of-sample performance and resilience to model misspecification. Additional results indicate that the robust strategies maintain reliable performance on real market data and remain effective during periods of market change. Our findings establish a practical and effective framework for robust deep hedging under realistic market uncertainties.