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.

翻译：可信机器学习（ML）社区日益认识到，模型在训练后能够选择性地“遗忘”数据点的能力至关重要。这引出了机器遗忘（MU）问题，其目标是在消除选定数据点对模型性能影响的同时，保持模型在遗忘后的效用。尽管已有多种用于消除数据影响的MU方法，但评估工作主要集中于随机数据遗忘，忽略了对应选择哪个子集才能真正衡量遗忘性能真实性的关键探究。为解决此问题，我们从对抗性视角为MU引入了一种新的评估角度。我们提出识别对影响消除构成最大挑战的数据子集，即确定最坏情况遗忘集。利用双层优化原理，我们在上层优化中放大遗忘挑战以模拟最坏情况，同时在下层进行标准训练与遗忘，实现数据影响消除与模型效用之间的平衡。我们的方案为MU的鲁棒性与有效性提供了最坏情况评估。通过对不同数据集（包括CIFAR-10、100、CelebA、Tiny ImageNet和ImageNet）和模型（包括图像分类器与生成模型）的大量实验，我们揭示了现有（近似）遗忘策略的关键优缺点。我们的结果阐明了MU在实际应用中的复杂挑战，为未来开发更准确、更鲁棒的遗忘算法提供了指导。代码发布于 https://github.com/OPTML-Group/Unlearn-WorstCase。