Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
Micah Goldblum, Liam Fowl, Tom Goldstein
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.
BibTeX
@inproceedings{NEURIPS2020_cfee3986,
author = {Goldblum, Micah and Fowl, Liam and Goldstein, Tom},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {17886--17895},
publisher = {Curran Associates, Inc.},
title = {Adversarially Robust Few-Shot Learning: A Meta-Learning Approach},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/cfee398643cbc3dc5eefc89334cacdc1-Paper.pdf},
volume = {33},
year = {2020}
}