Machine unlearning aims to selectively remove the influence of specific training samples to satisfy privacy regulations such as the GDPR's 'Right to be Forgotten'. However, many existing methods require access to the data being removed, exposing it to membership inference attacks and potential misuse of Personally Identifiable Information (PII). We address this critical challenge by proposing Shadow Unlearning, a novel paradigm of approximate unlearning, that performs machine unlearning on anonymized forget data without exposing PII. We further propose a novel privacy-preserving framework, Neuro-Semantic Projector Unlearning (NSPU) to achieve Shadow unlearning. To evaluate our method, we compile Multi-domain Fictitious Unlearning (MuFU) forget set across five diverse domains and introduce an evaluation stack to quantify the trade-off between knowledge retention and unlearning effectiveness. Experimental results on various LLMs show that NSPU achieves superior unlearning performance, preserves model utility, and enhances user privacy. Additionally, the proposed approach is at least 10 times more computationally efficient than standard unlearning approaches. Our findings foster a new direction for privacy-aware machine unlearning that balances data protection and model fidelity.

翻译：机器遗忘旨在选择性移除特定训练样本的影响，以满足如GDPR"被遗忘权"等隐私法规要求。然而，现有方法多需访问待删除数据，易遭受成员推理攻击并可能导致个人可识别信息（PII）的滥用。针对这一关键挑战，我们提出影子遗忘——一种新颖的近似遗忘范式，可在不暴露PII的情况下对匿名化遗忘数据执行机器遗忘。我们进一步提出神经语义投影器遗忘（NSPU）这一隐私保护框架来实现影子遗忘。为评估方法性能，我们构建了涵盖五个不同领域的多领域虚构遗忘（MuFU）数据集，并引入评估体系以量化知识保留与遗忘效果之间的权衡。在不同LLMs上的实验结果表明，NSPU在实现优异遗忘性能的同时，能有效保持模型效用并增强用户隐私。此外，该方法相比标准遗忘方案具有至少10倍的计算效率提升。我们的研究为平衡数据保护与模型保真度的隐私感知机器遗忘开辟了新方向。