Machine unlearning through fine-grained model parameters perturbation

TL;DR

This paper introduces fine-grained parameter perturbation strategies for machine unlearning that enhance privacy while maintaining computational efficiency and proposes new metrics and methods to evaluate unlearning effectiveness.

Contribution

It presents novel fine-grained unlearning techniques, new evaluation metrics, and a distribution perturbation method to better assess unlearning effectiveness.

Findings

Effective privacy protection with low computational costs.

Novel metrics for measuring unlearning and model retention.

SPD-GAN improves unlearning evaluation accuracy.

Abstract

Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weight perturbation-based unlearning is a general approach, but it typically involves globally modifying the parameters. We propose fine-grained Top-K and Random-k parameters perturbed inexact machine unlearning strategies that address the privacy needs while keeping the computational costs tractable. In order to demonstrate the efficacy of our strategies we also tackle the challenge of evaluating the effectiveness of machine unlearning by considering the model's generalization performance across both unlearning and remaining data. To better assess the unlearning effect and model generalization, we propose novel metrics, namely, the forgetting rate and memory retention rate. However, for inexact machine unlearning, current metrics are inadequate in quantifying the degree of forgetting that occurs after unlearning strategies are applied. To address this, we introduce SPD-GAN, which subtly perturbs the distribution of data targeted for unlearning. Then, we evaluate the degree of unlearning by measuring the performance difference of the models on the perturbed unlearning data before and after the unlearning process. By implementing these innovative techniques and metrics, we achieve computationally efficacious privacy protection in machine learning applications without significant sacrifice of model performance. Furthermore, this approach provides a novel method for evaluating the degree of unlearning.