Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable

Martin Andres Bertran, Shuai Tang, Michael Kearns, Jamie Heather Morgenstern, Aaron Roth, Steven Wu

Keywords: machine unlearning, reconstruction attack

Abstract: Machine unlearning is motivated by principles of data autonomy. The premise is that a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show that these updates expose individuals to high-accuracy reconstruction attacks which allow the attacker to recover their data in its entirety, even when the original models are so simple that privacy risk might not otherwise have been a concern. We show how to mount a near-perfect attack on the deleted data point from linear regression models. We then generalize our attack to other loss functions and architectures, and empirically demonstrate the effectiveness of our attacks across a wide range of datasets (capturing both tabular and image data). Our work highlights that privacy risk is significant even for extremely simple model classes when individuals can request deletion of their data from the model.

Primary Area: Privacy

Submission Number: 13089