RAAT harmonizes clean accuracy and adversarial robustness by using fixed reduced perturbations for boundary samples and Domain Interpolation Consistency Adversarial Regularization to align input and latent spaces.
Once-for-all adversarial train- ing: In-situ tradeoff between robustness and accuracy for free.Advances in Neural Information Processing Systems (NeurIPS)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
RAAT harmonizes clean accuracy and adversarial robustness by using fixed reduced perturbations for boundary samples and Domain Interpolation Consistency Adversarial Regularization to align input and latent spaces.