DePrompt: 大语言模型提示中个人可识别信息的脱敏与评估
DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts
AI总结：
针对大语言模型提示存在个人可识别信息泄露风险的问题，本文提出DePrompt框架，结合大模型微调与对抗生成式脱敏实现高精度隐私保护，并设计效用指标平衡隐私与可用性，实验验证其性能优于现有方法。
摘要：
提示是与大语言模型（LLM）交互的关键环节，广泛影响模型输出的准确性与可解释性。然而，要获取准确、高质量的响应，需要精准的提示，这不可避免地带来了严重的个人可识别信息（PII）泄露风险。为此，本文提出DePrompt——一种面向提示的脱敏保护与有效性评估框架，使用户能够安全、透明地使用大语言模型。具体而言，我们以大模型微调技术作为底层隐私保护方法，结合上下文属性定义隐私类型，实现高精度的PII实体识别。此外，通过分析提示脱敏场景中的关键特征，我们设计了对抗生成式脱敏方法，在保留重要语义内容的同时，切断标识符与隐私属性之间的关联。我们还提出了提示的效用评估指标，以更好地衡量并平衡隐私性与可用性。该框架适用于各类提示，还可扩展至依赖文本可用性的场景。通过与基准方法及其他模型方法的对比，实验评估表明，经我们方法脱敏后的提示具备更优的隐私保护效用与模型推理效果。
英文摘要：
Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts, which inevitably pose significant risks of personal identifiable information (PII) leakage. Therefore, this paper proposes DePrompt, a desensitization protection and effectiveness evaluation framework for prompt, enabling users to safely and transparently utilize LLMs. Specifically, by leveraging large model fine-tuning techniques as the underlying privacy protection method, we integrate contextual attributes to define privacy types, achieving high-precision PII entity identification. Additionally, through the analysis of key features in prompt desensitization scenarios, we devise adversarial generative desensitization methods that retain important semantic content while disrupting the link between identifiers and privacy attributes. Furthermore, we present utility evaluation metrics for prompt to better gauge and balance privacy and usability. Our framework is adaptable to prompts and can be extended to text usability-dependent scenarios. Through comparison with benchmarks and other model methods, experimental evaluations demonstrate that our desensitized prompt exhibit superior privacy protection utility and model inference results.
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。
