捉迷藏（HaS）：一种轻量级提示词隐私保护框架
Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection
AI总结：
本文提出HaS轻量级框架，通过训练小模型去匿名化LLM返回结果，在最小计算开销下实现提示词隐私保护，并在翻译和分类任务中达到隐私与效用的最佳平衡。
摘要：
众多公司已开始提供基于大型语言模型（LLM）的服务，如ChatGPT，这不可避免地引发了隐私担忧，因为用户的提示词会暴露给模型提供商。以往利用多方计算（MPC）进行安全推理的研究已被证明不适用于LLM应用，因其耗时且通信密集。虽然轻量级匿名化技术可以通过替换或掩蔽来保护提示词中的私人信息，但这些技术无法恢复被替换的敏感数据在LLM生成结果中的原始内容。在本文中，我们通过训练一个小的本地模型来去匿名化LLM返回的结果，以最小的计算开销扩展了匿名化技术的应用场景。我们引入了HaS框架，其中“H(ide)”和“S(eek)”分别代表其两个核心过程：隐藏私人实体以进行匿名化和寻找私人实体以进行去匿名化。为了定量评估HaS的隐私保护性能，我们提出了黑盒和白盒对抗模型。此外，我们进行了实验以评估HaS在翻译和分类任务中的可用性。实验结果表明，HaS框架在隐私保护和效用之间实现了最佳平衡。
英文摘要：
Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider. Previous research on secure reasoning using multi-party computation (MPC) has proven to be impractical for LLM applications due to its time-consuming and communication-intensive nature. While lightweight anonymization techniques can protect private information in prompts through substitution or masking, they fail to recover sensitive data replaced in the LLM-generated results. In this paper, we expand the application scenarios of anonymization techniques by training a small local model to de-anonymize the LLM's returned results with minimal computational overhead. We introduce the HaS framework, where "H(ide)" and "S(eek)" represent its two core processes: hiding private entities for anonymization and seeking private entities for de-anonymization, respectively. To quantitatively assess HaS's privacy protection performance, we propose both black-box and white-box adversarial models. Furthermore, we conduct experiments to evaluate HaS's usability in translation and classification tasks. The experimental findings demonstrate that the HaS framework achieves an optimal balance between privacy protection and utility.
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。
