A claim that same-class mixup combined with adversarial training provably reduces class-wise robustness disparity, but the theoretical support is invalid because it evaluates the classifier on the wrong distribution and uses incorrect Phi-difference formulas.
To be robust or to be fair: Towards fairness in adversarial training,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Learning Fair Robustness via Domain Mixup
A claim that same-class mixup combined with adversarial training provably reduces class-wise robustness disparity, but the theoretical support is invalid because it evaluates the classifier on the wrong distribution and uses incorrect Phi-difference formulas.