Robustness may be at odds with accuracy
We show that there exists an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of standard accuracy. We demonstrate that this trade-off between th...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
ICLR,
2021-03-05T14:59:33Z.
|
Subjects: | |
Online Access: | Get fulltext |