Provably Unlearnable Examples

arXiv:2405.03316v1 Announce Type: new
Abstract: The exploitation of publicly accessible data has led to escalating concerns regarding data privacy and intellectual property (IP) breaches in the age of artificial intelligence. As a strategy to safeguard both data privacy and IP-related domain knowledge, efforts have been undertaken to render shared data unlearnable for unauthorized models in the wild. Existing methods apply empirically optimized perturbations to the data in the hope of disrupting the correlation between the inputs and the corresponding labels …

abstract age artificial artificial intelligence arxiv breaches concerns cs.cr cs.lg data data privacy domain domain knowledge examples exploitation intellectual property intelligence knowledge privacy property render strategy type