Skip to yearly menu bar Skip to main content


Virtual presentation / poster accept

Transferable Unlearnable Examples

Jie Ren · Han Xu · Yuxuan Wan · Xingjun Ma · Lichao Sun · Jiliang Tang

Keywords: [ Unlearnable Examples ] [ Data Protection ] [ Deep Learning and representational learning ]


Abstract:

With more people publishing their personal data online, unauthorized data usage has become a serious concern. The unlearnable examples strategies have been introduced to prevent third parties from training on the data without permission. They add perturbations to the users’ data before publishing, so as 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 or datasets. To tackle this issue, we propose a novel unlearnable strategy based on Class-wise Separability Discriminant (CSD), which boosts the transferability of the unlearnable perturbations by enhancing the linear separability. Extensive experiments demonstrate the transferability of the unlearnable examples crafted by our proposed method across training settings and datasets.

Chat is not available.