IAM

TAG»ADVERSARIAL MACHINE LEARNING«

06thMAY2020

PROJECT

Adversarial training on location-optimized adversarial patches.

More ...

ARTICLE

Adversarial Training Has Higher Sample Complexity

Training on adversarial examples generated on-the-fly, so-called adversarial training, improves robustness against adversarial examples while incurring a significant drop in accuracy. This apparent trade-off between robustness and accuracy has been observed on many datasets and is argued to be inherent to adversarial training — or even unavoidable. In this article, based on my recent CVPR’19 paper, I show experimental results indicating that adversarial training can achieve the same accuracy as normal training, if more training examples are available. This suggests that adversarial training has higher sample complexity.

More ...