SOURCE-LINKED INTELLIGENCE

Leveraging Imperfect Restoration for Data Availability Attack

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

The abundance of online data is at risk of unauthorized usage in training deep learning models. To counter this, various Data Availability Attacks (DAAs) have been devised to make data unlearnable for such models by subtly perturbing the training data. However, existing attacks often excel against either Supervised Learning (SL) or Self-Supervised Learning (SSL) scenarios. Among these, a model-free approach that generates a Convolution-based Unlearnable Dataset (CUDA) stands out as the most robust DAA across both SSL and SL. Nonetheless, CUDA's effectiveness against SSL is underwhelming and it

Read original source ↗ Open in workspace

recordType

paper

region

Global