私有记忆编辑：将记忆转化为防御以增强大语言模型的数据隐私
Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models
AI总结：
本文提出私有记忆编辑（PME）方法，通过检测并编辑LLMs对训练数据中PII的记忆，将模型的记忆能力转化为隐私防御策略，在不影响底层语言模型的前提下有效降低隐私训练数据提取攻击的泄露量，甚至使攻击准确率降为零。
摘要：
大语言模型（LLMs）具有记忆能力，因此在海量不受控制的数据中，可能会记住不应被存储、进而不应被泄露的个人可识别信息（PII）。本文提出私有记忆编辑（PME）方法，用于防止私有数据泄露，将LLMs的记忆能力这一表面上的局限转化为强大的隐私防御策略。以往针对LLMs的攻击利用的是关于其训练数据的先验知识，而我们的方法旨在利用同类知识使模型更加鲁棒。我们检测被记忆的PII，然后通过编辑模型对其训练数据的知识来缓解PII的记忆。我们验证了该过程不会影响底层语言模型，同时使其对隐私训练数据提取攻击更具鲁棒性。我们证明PME在多种配置下能够有效减少泄露的PII数量，在某些情况下甚至将隐私攻击的准确率降至零。
英文摘要：
Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, consequently, not leaked. In this paper, we introduce Private Memorization Editing (PME), an approach for preventing private data leakage that turns an apparent limitation, that is, the LLMs' memorization ability, into a powerful privacy defense strategy. While attacks against LLMs have been performed exploiting previous knowledge regarding their training data, our approach aims to exploit the same kind of knowledge in order to make a model more robust. We detect a memorized PII and then mitigate the memorization of PII by editing a model knowledge of its training data. We verify that our procedure does not affect the underlying language model while making it more robust against privacy Training Data Extraction attacks. We demonstrate that PME can effectively reduce the number of leaked PII in a number of configurations, in some cases even reducing the accuracy of the privacy attacks to zero.
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。
