A random-shuffle attack that preserves one-dimensional feature distributions while destroying correlations can fool classifiers and, used as data augmentation, occasionally beats standard tabular generators on AUROC.
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
-
Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations
A random-shuffle attack that preserves one-dimensional feature distributions while destroying correlations can fool classifiers and, used as data augmentation, occasionally beats standard tabular generators on AUROC.