Harmonic Machine Learning Models are Robust

TL;DR

This paper presents Harmonic Robustness, a new method to evaluate the stability and explainability of machine learning models during training and inference, applicable to various model types and capable of detecting overfitting and adversarial vulnerabilities.

Contribution

It introduces Harmonic Robustness, a novel approach based on the harmonic mean property, for real-time robustness testing without ground-truth labels across diverse models.

Findings

Effectively detects overfitting in low-dimensional models

Measures adversarial vulnerability in high-dimensional models

Applicable during training and real-time inference

Abstract

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.