影子遗忘：一种面向LLM保真保留的无面孔遗忘的神经语义方法
Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs
AI总结：
提出影子遗忘范式，通过神经语义投影器遗忘（NSPU）框架在匿名化遗忘数据上实现机器遗忘，保护隐私的同时保持模型效用，计算效率提升至少10倍。
摘要：
机器遗忘旨在选择性地移除特定训练样本的影响，以满足GDPR等隐私法规的“被遗忘权”。然而，许多现有方法需要访问被移除的数据，使其暴露于成员推断攻击和个人身份信息（PII）的潜在滥用。我们通过提出影子遗忘（Shadow Unlearning）来解决这一关键挑战，这是一种新的近似遗忘范式，在不暴露PII的情况下对匿名化遗忘数据进行机器遗忘。我们进一步提出了一种新颖的隐私保护框架——神经语义投影器遗忘（NSPU），以实现影子遗忘。为了评估我们的方法，我们跨五个不同领域构建了多领域虚构遗忘（MuFU）遗忘集，并引入了一个评估栈来量化知识保留与遗忘效果之间的权衡。在各种大型语言模型上的实验表明，NSPU实现了优越的遗忘性能，保持了模型效用，并增强了用户隐私。此外，所提出的方法在计算效率上比标准遗忘方法至少高出10倍。我们的研究为隐私感知的机器遗忘开辟了新方向，平衡了数据保护与模型保真度。
英文摘要：
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 10x 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.
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。
