Harmonic Machine Learning Models are Robust

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, indicat...

Full description

Saved in:
Bibliographic Details
Main Authors Kersting, Nicholas S, Li, Yi, Mohanty, Aman, Obisesan, Oyindamola, Okochu, Raphael
Format Journal Article
LanguageEnglish
Published 29.04.2024
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.48550/arxiv.2404.18825