Machine Unlearning in Computer Vision: Foundations and Applications

Abstract

This tutorial aims to offer a comprehensive understanding of emerging machine unlearning (MU) techniques. These techniques are designed to accurately assess the impact of specific data points, classes, or concepts on model performance and efficiently eliminate their potentially harmful influence within a pre-trained model, in response to users’ unlearning requests. With the recent shift to foundation models, MU has become indispensable, as re-training from scratch is prohibitively costly in terms of time, computational resources, and finances. Consequently, the field has expanded beyond the realm of security and privacy (SP) to include the removal of toxic content, copyright material, harmful information, and personally identifying data. Despite increasing research interest, MU for vision tasks remains significantly underexplored compared to its prominence in the SP field. Therefore, it is crucial to meticulously review, thoroughly explore, and comprehensively survey MU for computer vision (CV) through this tutorial. Within this tutorial, we will delve into the algorithmic foundations of MU methods, including techniques such as localization-informed unlearning, unlearning-focused finetuning, and vision model-specific optimizers. We will provide a comprehensive and clear overview of the diverse range of applications for MU in CV. Furthermore, we will emphasize the importance of unlearning from an industry perspective, where modifying the model during its life-cycle is preferable to re-training it entirely, and where metrics to verify the unlearning process become paramount. Our tutorial will furnish the general audience with sufficient background information to grasp the motivation, research progress, opportunities, and ongoing challenges in MU.