Solver-Integrated Adversarial Attacking and Training of Neural Operators
cs.LG
Submitted: 2025-10-21
Updated: 2026-10-29
License: http://creativecommons.org/licenses/by/4.0/
The gist: Neural operators are widely used as fast surrogates for numerical PDE solvers, mapping input functions to solution functions.
Terminology
Abstract
Neural operators are widely used as fast surrogates for numerical PDE solvers, mapping input functions to solution functions. However, their generalizability and robustness are not yet clearly defined in the operator-learning setting, which differs from traditional adversarial robustness definitions. This paper studies the generalizability and robustness of a learned neural operator from a solver-integrated perspective, addressing the challenge that the output of a learned operator and a numerical solver tends to change in tandem under input perturbation. First, we formalize the definition of generalization and robustness through a model-solver error operator, identifying fixed-input model-solver loss as generalization metric, and norm-bounded adversarial attack loss increase and Jacobian-error function norm as robustness metric. Second, we identify the solver-integrated adversarial attack as appropriate for PDE operator learning and show why model-only or fixed-ground-truth attacks can be insufficient when the solver output also changes with the input. Third, we develop solver-integrated adversarial training methods for neural operators. Experiments on representative PDE benchmarks show that this solver-integrated adversarial training clearly improves both generalizability and robustness. Deeper solver integration yields more effective attacks, more informative samples, and more efficient training than less integrated alternatives. These results provide a general framework for robust operator training and automatic sample selection without heavy manual intervention. More broadly, the formulation applies to adversarial regression whenever a ground-truth oracle can evaluate, and ideally differentiate, the true input-output map; PDE operator learning is one such case.
Sources
- Adversarial Autoencoders in Operator Learning
- StablePDENet: Enhancing Neural Operator Stability through Physics-Informed Residual-Sensitivity Regularization
- Learning Turbulent Flows with Generative Models: Super-resolution, Forecasting, and Sparse Flow Reconstruction
- RAMS: Residual-based adversarial-gradient moving sample method for scientific machine learning in solving partial differential equations
- Beyond Uniform Sampling: Synergistic Active Learning and Input Denoising for Robust Neural Operators
- Adversarial Vulnerabilities in Neural Operator Digital Twins: Gradient-Free Attacks on Nuclear Thermal-Hydraulic Surrogates
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis