Models trained against adversarial attacks first learn class-shared features, then forget them as robust overfitting sets in, and preserving these features explains why soft-label training helps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Identifying and Understanding Cross-Class Features in Adversarial Training
Models trained against adversarial attacks first learn class-shared features, then forget them as robust overfitting sets in, and preserving these features explains why soft-label training helps.