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.
Detection and identification of uavs based on spectrum monitoring and deep learning in negative snr conditions
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.