Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy

arXiv:2403.01218v1 Announce Type: new
Abstract: The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a model has unlearned, an adversary that interacts with the model should no longer be able to tell whether the unlearned example was included in the model's training set or not. In the privacy literature, this is known as …

abstract arxiv cost cs.cr cs.lg example false influence privacy scratch sense training type unlearning