标题： IMU：影响引导的机器遗忘 显示英文标题

标题： IMU: Influence-guided Machine Unlearning

摘要： 最近的研究表明，深度学习模型容易受到攻击，并倾向于记忆训练数据点，这引发了关于隐私泄露的重大担忧。 这促使了机器遗忘（MU）的发展，即一种使模型能够根据请求选择性地遗忘特定数据点的范式。 然而，大多数现有的MU算法需要在保留集上进行部分或完全的微调。 这需要持续访问原始训练数据，由于隐私问题和存储限制，这通常是不现实的。 已经提出了一些无需保留数据的MU方法，但其中一些依赖于对辅助数据和保留集的预计算统计信息的访问，而另一些在遗忘较大比例的数据时扩展性较差。 在本文中，我们提出了基于影响的机器遗忘（IMU），这是一种简单而有效的方法，仅使用遗忘集进行机器遗忘。 具体来说，IMU采用梯度上升，并创新性地根据数据点的影响动态分配遗忘强度。 这种自适应策略显著提高了遗忘效果，同时保持了模型的实用性。 在视觉和语言任务中的结果表明，IMU始终优于现有的无需保留数据的MU方法。 显示英文摘要

摘要： Recent studies have shown that deep learning models are vulnerable to attacks and tend to memorize training data points, raising significant concerns about privacy leakage. This motivates the development of machine unlearning (MU), i.e., a paradigm that enables models to selectively forget specific data points upon request. However, most existing MU algorithms require partial or full fine-tuning on the retain set. This necessitates continued access to the original training data, which is often impractical due to privacy concerns and storage constraints. A few retain-data-free MU methods have been proposed, but some rely on access to auxiliary data and precomputed statistics of the retain set, while others scale poorly when forgetting larger portions of data. In this paper, we propose Influence-guided Machine Unlearning (IMU), a simple yet effective method that conducts MU using only the forget set. Specifically, IMU employs gradient ascent and innovatively introduces dynamic allocation of unlearning intensities across different data points based on their influences. This adaptive strategy significantly enhances unlearning effectiveness while maintaining model utility. Results across vision and language tasks demonstrate that IMU consistently outperforms existing retain-data-free MU methods.