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.
@article{arxiv.2404.18825,
title = {Harmonic Machine Learning Models are Robust},
author = {Nicholas S. Kersting and Yi Li and Aman Mohanty and Oyindamola Obisesan and Raphael Okochu},
journal= {arXiv preprint arXiv:2404.18825},
year = {2024}
}