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

Part of Advances in Neural Information Processing Systems 33 (NeurIPS 2020)

AuthorFeedback »Bibtex »MetaReview »Paper »Review »Supplemental »


Micah Goldblum, Liam Fowl, Tom Goldstein


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.