Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning

arXiv:2404.03233v1 Announce Type: new
Abstract: Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning mainly focus on the efficacy and efficiency of unlearning methods, while neglecting the investigation of the privacy vulnerability during the unlearning process. With two versions of a model available to an adversary, that is, the original model and the unlearned model, …

arxiv attacks can cs.cr data deletion efficiency focus learn machine machine learning machine learning models request right to be forgotten solution studies under