English

Adversarially Robust Few-Shot Learning: A Meta-Learning Approach

Machine Learning 2020-10-16 v3 Machine Learning

Abstract

Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial examples. The goal of our work is to produce networks which both perform well at few-shot classification tasks and are simultaneously robust to adversarial examples. We develop an algorithm, called Adversarial Querying (AQ), for producing adversarially robust meta-learners, and we thoroughly investigate the causes for adversarial vulnerability. Moreover, our method achieves far superior robust performance on few-shot image classification tasks, such as Mini-ImageNet and CIFAR-FS, than robust transfer learning.

Keywords

Cite

@article{arxiv.1910.00982,
  title  = {Adversarially Robust Few-Shot Learning: A Meta-Learning Approach},
  author = {Micah Goldblum and Liam Fowl and Tom Goldstein},
  journal= {arXiv preprint arXiv:1910.00982},
  year   = {2020}
}

Comments

Accepted to NeurIPS 2020

R2 v1 2026-06-23T11:32:48.050Z