Adversarial training on simplified Vision Transformers achieves benign overfitting with near-zero robust loss and generalization error when signal-to-noise ratio and perturbation budget meet specific conditions.
International conference on machine learning , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
citing papers explorer
-
Benign Overfitting in Adversarial Training for Vision Transformers
Adversarial training on simplified Vision Transformers achieves benign overfitting with near-zero robust loss and generalization error when signal-to-noise ratio and perturbation budget meet specific conditions.
-
Compositional Adversarial Training for Robust Visual Watermarking
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.