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

2019/10/02 by Goldblum, Micah, Fowl, Liam, Goldstein, Tom
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1910.00982

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.

Related

• Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks
• A Simple Approach to Adversarial Robustness in Few-shot Image Classification
• Can we achieve robustness from data alone?
• Learning from Few Samples: A Survey
• Robust Few-shot Learning Without Using any Adversarial Samples