Dual-branch Robust Unlearnable Examples

Unlearnable examples (UEs) aim to compromise model training by injecting imperceptible perturbations to clean samples. However, certain existing UE schemes exhibit limited robustness against advanced defenses due to their heuristic design or narrowly scoped domain perturbations. To address this, we propose DUNE, a Dualbranch UNlearnable Ensemble perturbation optimization approach. Specifically, DUNE separately optimizes perturbations in the spatial and color domains to establish the mapping between perturbations and shift-induced labels. This design extends the perturbation domain to increase noise intensity for improving robustness and drives the models to learn perturbation-oriented features with degraded generalization, thereby achieving unlearnability. To strengthen DUNE's performance, we further propose an unlearnabilityenhancing ensemble strategy that aggregates diverse pre-trained models during the dual-branch optimization. Extensive experiments on benchmark datasets CIFAR-10 and ImageNet verify that DUNE's robustness outperforms 12 SOTA UE schemes under 7 mainstream defenses, yielding a lower average test accuracy of 14.95% to 50.82%. The code is available at https: //github.com/wxldragon/DUNE .