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.
Cat: Customized adversarial training for improved robustness
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.