对抗知识侵蚀和遗忘逆转的鲁棒持续卸载
Robust Continual Unlearning against Knowledge Erosion and Forgetting Reversal
AI总结：
本文提出SAFER框架，通过保持保留数据的表示稳定性并施加负对数边际，有效缓解持续卸载中的知识侵蚀和遗忘逆转问题，实现多阶段稳定性能。
摘要：
作为一种平衡人工智能行业增长与隐私保护需求的手段，机器卸载在实现人工智能中的'被遗忘权'中起着关键作用。该技术使AI系统能够移除特定数据的影响，同时保持其余学习知识。尽管已广泛研究，大多数现有卸载方法假设卸载仅进行一次。在本工作中，我们评估了现有卸载算法在更现实的多次卸载场景中的表现，并在此设置中识别出两个关键现象：（1）知识侵蚀，即在卸载阶段中保留数据的准确性逐步退化；（2）遗忘逆转，即先前遗忘的样本在后期阶段再次变得可识别。为了解决这些挑战，我们提出SAFER（Stability-preserving Forgetting with Effective Regularization），一种持续卸载框架，通过保持保留数据的表示稳定性并施加负对数边际来处理遗忘数据。广泛实验表明，SAFER不仅缓解了知识侵蚀，还缓解了遗忘逆转，实现了多个卸载阶段的稳定性能。
英文摘要：
As a means to balance the growth of the AI industry with the need for privacy protection, machine unlearning plays a crucial role in realizing the ``right to be forgotten'' in artificial intelligence. This technique enables AI systems to remove the influence of specific data while preserving the rest of the learned knowledge. Although it has been actively studied, most existing unlearning methods assume that unlearning is performed only once. In this work, we evaluate existing unlearning algorithms in a more realistic scenario where unlearning is conducted repeatedly, and in this setting, we identify two critical phenomena: (1) Knowledge Erosion, where the accuracy on retain data progressively degrades over unlearning phases, and (2) Forgetting Reversal, where previously forgotten samples become recognizable again in later phases. To address these challenges, we propose SAFER (StAbility-preserving Forgetting with Effective Regularization), a continual unlearning framework that maintains representation stability for retain data while enforcing negative logit margins for forget data. Extensive experiments show that SAFER mitigates not only knowledge erosion but also forgetting reversal, achieving stable performance across multiple unlearning phases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
