Extends TRADES to a Wasserstein distributional threat with an efficient budgeted attack, and fine-tunes pre-trained robust models to improve a self-defined distributional robustness metric.
Title resolution pending
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
-
Wasserstein distributional adversarial training for deep neural networks
Extends TRADES to a Wasserstein distributional threat with an efficient budgeted attack, and fine-tunes pre-trained robust models to improve a self-defined distributional robustness metric.