A Comparative Study of Machine Unlearning Techniques for Image and Text Classification Models

TL;DR

This paper compares six leading machine unlearning techniques for image and text classification, assessing their performance, efficiency, and regulatory compliance to guide ethical and adaptable AI development.

Contribution

It provides a systematic comparative analysis of unlearning methods, highlighting their strengths, limitations, and practical applicability in AI models.

Findings

Different techniques vary in efficiency and accuracy

Some methods better ensure compliance with privacy regulations

Tradeoffs exist between unlearning speed and model performance

Abstract

Machine Unlearning has emerged as a critical area in artificial intelligence, addressing the need to selectively remove learned data from machine learning models in response to data privacy regulations. This paper provides a comprehensive comparative analysis of six state-of-theart unlearning techniques applied to image and text classification tasks. We evaluate their performance, efficiency, and compliance with regulatory requirements, highlighting their strengths and limitations in practical scenarios. By systematically analyzing these methods, we aim to provide insights into their applicability, challenges,and tradeoffs, fostering advancements in the field of ethical and adaptable machine learning.