通过私有关联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
AI总结：
本文提出Private Association Editing（PAE）方法，无需重新训练即可移除LLMs中的个人身份信息，有效防止私有数据泄露，相比基线方法表现更优，为实际应用提供更安全的模型。
摘要：
大型语言模型（LLMs）由于其文本生成能力，在数据密集型应用中需要重新设计方案以保护隐私。事实上，LLMs在受到恶意提示时往往会记忆并泄露私人信息。本文引入了Private Association Editing（PAE）作为一种防止私有数据泄露的新防御方法。PAE旨在无需重新训练模型的情况下有效移除个人身份信息（PII）。实验结果表明，PAE相对于其他基线方法具有有效性。我们相信PAE将成为保护LLMs数据隐私的重要工具，推动开发更安全的实际应用模型。
英文摘要：
Large language models (LLMs) require a significant redesign in solutions to preserve privacy in data-intensive applications due to their text-generation capabilities. Indeed, LLMs tend to memorize and emit private information when maliciously prompted. In this paper, we introduce Private Association Editing (PAE) as a novel defense approach for private data leakage. PAE is designed to effectively remove Personally Identifiable Information (PII) without retraining the model. Experimental results demonstrate the effectiveness of PAE with respect to alternative baseline methods. 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.
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。
