Harmonic Machine Learning Models are Robust
This addresses the need for real-time robustness testing in ML models, though it appears incremental as it builds on existing concepts of harmonic properties.
The authors tackled the problem of assessing machine learning model robustness without ground-truth labels by introducing Harmonic Robustness, a method that identifies overfitting and adversarial vulnerabilities, as demonstrated in models like ResNet-50 and Vision Transformer.
We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels. It is based on functional deviation from the harmonic mean value property, indicating instability and lack of explainability. We show implementation examples in low-dimensional trees and feedforward NNs, where the method reliably identifies overfitting, as well as in more complex high-dimensional models such as ResNet-50 and Vision Transformer where it efficiently measures adversarial vulnerability across image classes.