Unlearnable examples fail under pretraining-finetuning due to semantic filtering by frozen layers, but Shallow Semantic Camouflage restores effectiveness by confining perturbations to semantically valid subspaces.
author Gao, X
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
DUNE optimizes perturbations in spatial and color domains with model ensembles to produce robust unlearnable examples that reduce test accuracy to 14.95%-50.82% under 7 defenses on CIFAR-10 and ImageNet, outperforming 12 prior methods.
Catastrophic overfitting in fast adversarial training is reinterpreted as a weak-trigger variant of unlearnable tasks, allowing backdoor-inspired recalibration and outlier suppression to restore robustness.
Nonlinear transformations enable DNNs to achieve substantial test accuracy gains (0.34% to 249.59%) on unlearnable CIFAR10 datasets from twelve protection methods, outperforming a recent linear baseline.
citing papers explorer
-
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
Unlearnable examples fail under pretraining-finetuning due to semantic filtering by frozen layers, but Shallow Semantic Camouflage restores effectiveness by confining perturbations to semantically valid subspaces.
-
Dual-branch Robust Unlearnable Examples
DUNE optimizes perturbations in spatial and color domains with model ensembles to produce robust unlearnable examples that reduce test accuracy to 14.95%-50.82% under 7 defenses on CIFAR-10 and ImageNet, outperforming 12 prior methods.
-
Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
Catastrophic overfitting in fast adversarial training is reinterpreted as a weak-trigger variant of unlearnable tasks, allowing backdoor-inspired recalibration and outlier suppression to restore robustness.
-
Nonlinear Transformations Against Unlearnable Datasets
Nonlinear transformations enable DNNs to achieve substantial test accuracy gains (0.34% to 249.59%) on unlearnable CIFAR10 datasets from twelve protection methods, outperforming a recent linear baseline.