Delta energy, the energy gap between an image and its adversarial counterpart, separates catastrophic from robust overfitting, and penalizing it with the DER regularizer mitigates both while improving generation diversity.
Improving adversarial robustness requires revisiting misclassified examples,
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
-
Understanding Adversarial Training with Energy-based Models
Delta energy, the energy gap between an image and its adversarial counterpart, separates catastrophic from robust overfitting, and penalizing it with the DER regularizer mitigates both while improving generation diversity.