MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

TL;DR

This paper introduces MPU, a privacy-preserving framework for unlearning in large language models that uses multiple perturbed copies to enable local unlearning without revealing server parameters.

Contribution

MPU provides a novel, algorithm-agnostic approach for privacy-preserving unlearning by distributing perturbed model copies and aggregating updates, improving privacy without sacrificing performance.

Findings

MPU achieves unlearning performance close to noise-free baselines.

Most algorithms' performance degradation is below 1% with up to 10% noise.

MPU can outperform noise-free baselines for some algorithms under 1% noise.

Abstract

Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose MPU, an algorithm-agnostic privacy-preserving Multiple Perturbed Copies Unlearning framework that primarily introduces two server-side modules: Pre-Process for randomized copy generation and Post-Process for update aggregation. In Pre-Process, the server distributes multiple perturbed and reparameterized model instances, allowing the client to execute unlearning locally on its private forget set without accessing the server's exact original parameters. After local unlearning, the server performs Post-Process by inverting the reparameterization and aggregating updates with a harmonic denoising procedure to alleviate the impact of perturbation. Experiments with seven unlearning algorithms show that MPU achieves comparable unlearning performance to noise-free baselines, with most algorithms' average degradation well below 1% up to 10% noise, and can even outperform the noise-free baseline for some algorithms under 1% noise. Code is available at https://github.com/Tristan0318/MPU.