An adaptive l^p norm control in FGSM adversarial training, guided by participation ratio and entropy of gradients, mitigates catastrophic overfitting without noise or regularization.
Apr-net: Defense against adversarial examples based on universal adversarial perturbation removal network.IEEE Transactions on Artificial Intelligence, 6(4):945–954, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training
An adaptive l^p norm control in FGSM adversarial training, guided by participation ratio and entropy of gradients, mitigates catastrophic overfitting without noise or regularization.