Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning

TL;DR

This paper introduces a novel approach using adversarial examples, called Guiding Adversarial Examples (GAEs), to improve minority class accuracy in imbalanced learning scenarios, showing promising results on benchmark datasets.

Contribution

The paper presents the first method leveraging adversarial examples to address imbalanced learning by adjusting decision boundaries with GAEs.

Findings

Effective increase in minority class accuracy

Comparable performance to state-of-the-art methods

Minimal impact on majority class accuracy

Abstract

Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes. In this paper, we demonstrate that adversarial examples can also be utilized for good to improve the performance of imbalanced learning. We provide a new perspective on how to deal with imbalanced data: adjust the biased decision boundary by training with Guiding Adversarial Examples (GAEs). Our method can effectively increase the accuracy of minority classes while sacrificing little accuracy on majority classes. We empirically show, on several benchmark datasets, our proposed method is comparable to the state-of-the-art method. To our best knowledge, we are the first to deal with imbalanced learning with adversarial examples.