Adversarial Training for Physics-Informed Neural Networks

1 code implementation • 18 Oct 2023 • Yao Li, Shengzhu Shi, Zhichang Guo, Boying Wu

AT-PINNs enhance the robustness of PINNs by fine-tuning the model with adversarial samples, which can accurately identify model failure locations and drive the model to focus on those regions during training.

Adversarial Attack