Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation

TL;DR

This paper introduces a novel zero-shot machine unlearning method using layer-wise relevance analysis and neuronal path perturbation to effectively remove data influence while preserving model utility and ensuring privacy.

Contribution

It proposes a new approach combining relevance analysis and neuronal perturbation for effective zero-shot unlearning with privacy guarantees.

Findings

Successfully removes targeted data from models

Maintains high model utility after unlearning

Provides privacy protection during unlearning process

Abstract

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for extensive retraining. However, it faces several key challenges, including accurately implementing unlearning, ensuring privacy protection during the unlearning process, and achieving effective unlearning without significantly compromising model performance. This paper presents a novel approach to machine unlearning by employing Layer-wise Relevance Analysis and Neuronal Path Perturbation. We address three primary challenges: the lack of detailed unlearning principles, privacy guarantees in zero-shot unlearning scenario, and the balance between unlearning effectiveness and model utility. Our method balances machine unlearning performance and model utility by identifying and perturbing highly relevant neurons, thereby achieving effective unlearning. By using data not present in the original training set during the unlearning process, we satisfy the zero-shot unlearning scenario and ensure robust privacy protection. Experimental results demonstrate that our approach effectively removes targeted data from the target unlearning model while maintaining the model's utility, offering a practical solution for privacy-preserving machine learning.