To be Robust or to be Fair: Towards Fairness in Adversarial Training

Han Xu
Han Xu
Yaxin Li
Yaxin Li
Cited by: 1|Views30

Abstract:

Adversarial training algorithms have been proven to be reliable to improve machine learning models' robustness against adversarial examples. However, we find that adversarial training algorithms tend to introduce severe disparity of accuracy and robustness between different groups of data. For instance, PGD adversarially trained ResNet1...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments