Efficient Unlearning with Privacy Guarantees

TL;DR

This paper introduces EUPG, a machine unlearning framework that provides formal privacy guarantees, enabling efficient data removal from models while maintaining utility and reducing costs.

Contribution

EUPG is a novel unlearning framework that combines privacy models with efficient unlearning, offering formal guarantees and practical performance improvements.

Findings

EUPG achieves utility comparable to exact unlearning methods.

EUPG significantly reduces computational and storage costs.

EUPG effectively unlearns data protected with k-anonymity and differential privacy.

Abstract

Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning has emerged as a practical means to facilitate model forgetting of data instances seen during training. Although some existing machine unlearning methods guarantee exact forgetting, they are typically costly in computational terms. On the other hand, more affordable methods do not offer forgetting guarantees and are applicable only to specific ML models. In this paper, we present \emph{efficient unlearning with privacy guarantees} (EUPG), a novel machine unlearning framework that offers formal privacy guarantees to individuals whose data are being unlearned. EUPG involves pre-training ML models on data protected using privacy models, and it enables {\em efficient unlearning with the privacy guarantees offered by the privacy models in use}. Through empirical evaluation on four heterogeneous data sets protected with $k$-anonymity and $\epsilon$-differential privacy as privacy models, our approach demonstrates utility and forgetting effectiveness comparable to those of exact unlearning methods, while significantly reducing computational and storage costs. Our code is available at https://github.com/najeebjebreel/EUPG.