Year: 2022
Type: article
Abstract: Scope of ReproducibilityThis work attempts to reproduce the results of the 2021 ICML paper To be Robust or to be Fair: Towards Fairness in Adversarial Training.I first reproduce classwise accuracy and robustness discrepancies resulting from adversarial training, and then implement the authors' proposed Fair Robust Learning (FRL) algorithms for correcting this bias.
Author: Hardy, Ian
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4281399990
