Machine Unlearning (MU) is to forget data from a well-trained model, which is
practically important due to the "right to be forgotten". In this paper, we
start from the fundamental distinction between training data and unseen data on
their contribution to the model: the training data contributes to the final
model while the unseen data does not. We theoretically discover that the input
sensitivity can approximately measure the contribution and practically design
an algorithm, called MU-Mis (machine unlearning via minimizing input
sensitivity), to suppress the contribution of the forgetting data. Experimental
results demonstrate that MU-Mis outperforms state-of-the-art MU methods
significantly. Additionally, MU-Mis aligns more closely with the application of
MU as it does not require the use of remaining data.

机器遗忘（MU）是遗忘一个经过训练的模型中的数据，这是非常重要的，因为要保护 “被遗忘权”。本文从训练数据和未知数据对模型的贡献之间的基本区别出发，理论上发现输入灵敏度可以近似度量贡献，并实际设计了一个名为 MU-Mis（通过最小化输入灵敏度进行机器遗忘）的算法，以抑制遗忘数据的贡献。实验结果表明，MU-Mis 在很大程度上优于最先进的 MU 方法。此外，MU-Mis 与 MU 的应用更加密切，因为它不需要使用剩余数据。