Large Language Models (LLMs) are powerful tools with extensive applications,
but their tendency to memorize private information raises significant concerns
as private data leakage can easily happen. In this paper, we introduce Private
Association Editing (PAE), a novel defense approach for private data leakage.
PAE is designed to effectively remove Personally Identifiable Information (PII)
without retraining the model. Our approach consists of a four-step procedure:
detecting memorized PII, applying PAE cards to mitigate memorization of private
data, verifying resilience to targeted data extraction (TDE) attacks, and
ensuring consistency in the post-edit LLMs. The versatility and efficiency of
PAE, which allows for batch modifications, significantly enhance data privacy
in LLMs. Experimental results demonstrate the effectiveness of PAE in
mitigating private data leakage. We believe PAE will serve as a critical tool
in the ongoing effort to protect data privacy in LLMs, encouraging the
development of safer models for real-world applications.

利用私有关联编辑（Private Association Editing，PAE）的方法，本研究针对大型语言模型（Large Language Models，LLMs）的私人数据泄露问题进行了防御，在不重新训练模型的情况下，有效地移除个人可识别信息（Personally Identifiable Information，PII）。通过四个步骤的程序，包括检测存储的 PII、使用 PAE 卡片减少私有数据的记忆、验证对目标数据提取（Targeted Data Extraction，TDE）攻击的韧性以及确保后编辑的 LLMs 的一致性，PAE 在 LLMs 的数据隐私方面显著提升了多项修改的灵活性和效率。实验结果显示 PAE 在减轻私人数据泄露方面的有效性。我们相信 PAE 将成为保护 LLMs 数据隐私的关键工具，鼓励开发更安全的用于现实世界应用的模型。

通过私有化联合编辑增强大型语言模型的数据隐私

Enhancing Data Privacy in Large Language Models through Private  Association Editing

Large language models pretrained on a huge amount of data capture rich
knowledge and information in the training data. The ability of data
memorization and regurgitation in pretrained language models, revealed in
previous studies, brings the risk of data leakage. In order to effectively
reduce these risks, we propose a framework DEPN to Detect and Edit Privacy
Neurons in pretrained language models, partially inspired by knowledge neurons
and model editing. In DEPN, we introduce a novel method, termed as privacy
neuron detector, to locate neurons associated with private information, and
then edit these detected privacy neurons by setting their activations to zero.
Furthermore, we propose a privacy neuron aggregator dememorize private
information in a batch processing manner. Experimental results show that our
method can significantly and efficiently reduce the exposure of private data
leakage without deteriorating the performance of the model. Additionally, we
empirically demonstrate the relationship between model memorization and privacy
neurons, from multiple perspectives, including model size, training time,
prompts, privacy neuron distribution, illustrating the robustness of our
approach.

为了有效降低预训练语言模型中的数据泄漏风险，我们提出了一个名为 DEPN 的框架来检测和编辑预训练语言模型中的隐私神经元，部分受到知识神经元和模型编辑的启发。在 DEPN 中，我们引入了一种称为隐私神经元探测器的新方法，来定位与私人信息相关的神经元，并通过将它们的激活设置为零来编辑这些检测到的隐私神经元。此外，我们还提出了一种批处理方式的隐私神经元聚合器来去除隐私信息。实验结果表明，我们的方法能够显著并有效地降低私人数据泄漏的风险，而不会损害模型的性能。此外，我们从多个角度（包括模型大小、训练时间、提示、隐私神经元分布）经验性地展示了模型记忆和隐私神经元之间的关系，从而证明了我们方法的稳健性。