Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
Authors:
- Chongyu FanCFChongyu Fan
- Jiancheng LiuJLJiancheng Liu
Preprint
Abstract
The trustworthy machine learning (ML) community is increasingly recognizing the crucial need for models capable of selectively 'unlearning' data points after training. This leads to the problem of machine unlearning (MU), aiming to eliminate the influence of chosen data points on model performance, while still maintaining the model's utility post-unlearning. Despite various MU methods for data influence erasure, evaluations have largely focused on random data forgetting, ignoring the vital inquiry into which subset should be chosen to truly gauge the authenticity of unlearning performance. To tackle this issue, we introduce a new evaluative angle for MU from an adversarial viewpoint. We propose identifying the data subset that presents the most significant challenge for influence erasure, i.e., pinpointing the worst-case forget set. Utilizing a bi-level optimization principle, we amplify unlearning challenges at the upper optimization level to emulate worst-case scenarios, while simultaneously engaging in standard training and unlearning at the lower level, achieving a balance between data influence erasure and model utility. Our proposal offers a worst-case evaluation of MU's resilience and effectiveness. Through extensive experiments across different datasets (including CIFAR-10, 100, CelebA, Tiny ImageNet, and ImageNet) and models (including both image classifiers and generative models), we expose critical pros and cons in existing (approximate) unlearning strategies. Our results illuminate the complex challenges of MU in practice, guiding the future development of more accurate and robust unlearning algorithms. The code is available at https://github.com/OPTML-Group/Unlearn-WorstCase.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Rethinking machine unlearning for large language modelsNature Machine Intelligence, 2025
- To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy to Generate Unsafe Images ... For Now2024
- Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models2024
- AI model disgorgement: Methods and choicesProceedings of the National Academy of Sciences, 2024
- Ablating Concepts in Text-to-Image Diffusion Models2023
- Erasing Concepts from Diffusion Models2023
- Federated Unlearning: Guarantee the Right of Clients to ForgetIEEE Network, 2022
- The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining2022
- Backdoor Defense with Machine Unlearning2022
- The European Union general data protection regulation: what it is and what it meansInformation & Communications Technology Law, 2019