Transferable Unlearnable Examples
This addresses the issue of unauthorized data usage for data owners by making unlearnable strategies more robust, though it is incremental as it builds on existing unlearnable methods.
The paper tackles the problem of unlearnable examples losing effectiveness when transferred to different training settings and datasets, proposing a method based on Classwise Separability Discriminant that enhances linear separability to improve transferability, with experiments showing successful transfer across settings and datasets.
With more people publishing their personal data online, unauthorized data usage has become a serious concern. The unlearnable strategies have been introduced to prevent third parties from training on the data without permission. They add perturbations to the users' data before publishing, which aims to make the models trained on the perturbed published dataset invalidated. These perturbations have been generated for a specific training setting and a target dataset. However, their unlearnable effects significantly decrease when used in other training settings and datasets. To tackle this issue, we propose a novel unlearnable strategy based on Classwise Separability Discriminant (CSD), which aims to better transfer the unlearnable effects to other training settings and datasets by enhancing the linear separability. Extensive experiments demonstrate the transferability of the proposed unlearnable examples across training settings and datasets.