Saved in:
Bibliographic Details
Main Authors: Kersting, Nicholas S., Li, Yi, Mohanty, Aman, Obisesan, Oyindamola, Okochu, Raphael
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.18825
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917652719468544
author Kersting, Nicholas S.
Li, Yi
Mohanty, Aman
Obisesan, Oyindamola
Okochu, Raphael
author_facet Kersting, Nicholas S.
Li, Yi
Mohanty, Aman
Obisesan, Oyindamola
Okochu, Raphael
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_18825
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Harmonic Machine Learning Models are Robust
Kersting, Nicholas S.
Li, Yi
Mohanty, Aman
Obisesan, Oyindamola
Okochu, Raphael
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title Harmonic Machine Learning Models are Robust
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.18825