Physics-guided unlearning improves safety in cyber-physical systems
Physics-Aware Machine Unlearning for Cyber-Physical Systems
Machine Learning
Summary
Sometimes machine learning models can learn bad or harmful behaviors, called poison, that need to be removed safely. This paper explains a way to teach a model to forget harmful data while also making sure it respects the physical rules of the system it controls. The method uses physics knowledge to guide corrections, avoiding changes that would break real-world constraints. The authors tested this approach on a simulated electric power system, showing it can remove harmful behavior and keep the system working safely.
What this means in practice
- •For power system operators: Remove harmful training data from AI controllers of electric grids while ensuring they obey physical laws.
- •For industrial control engineers: Improve safety when correcting AI models by integrating physical system constraints during model adjustments.
Authors
Mohammad Zakaria Haider, Muhammad Nadeem, Mohammad Ashiqur Rahman
Abstract
This paper proposes a physics-guided gradient-ascent-based machine unlearning method that couples the forgetting signal with the physical residual of the target cyber-physical systems, ensuring that weight updates during unlearning are steered toward physically feasible regions of the weight space. The physics residual acts as a safety fence during gradient ascent: the model is steered away from the poisoned behavioral basin and simultaneously toward physics-compliant territory, rather than toward an arbitrary alternative that may still violate domain constraints. We evaluate the proposed method against four baselines: naive gradient ascent, exact unlearning, SISA, and full retraining on an IEEE 34-bus distribution system, driven by two physics-informed neural network-based distribution energy resource controllers and validated through high-fidelity OpenDSS power-flow co-simulation. From the evaluation, we found that our proposed physics-guided model simultaneously removes poison and restores physical compliance, which are essential for the safe deployment of safety-critical cyber-physical systems