聊天机器人准备好应对隐私敏感型应用了吗？对输入复现与提示诱导净化的调查
Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization
AI总结：
本文探究了ChatGPT在隐私敏感应用中的输入复现问题，发现其逐字保留PII的比例达57.4%且存在子群体差异，同时验证了通过提示诱导遵循法规可显著减少PII输出。
摘要：
基于LLM的聊天机器人正被广泛应用于医疗保健、个人助理、企业招聘决策等领域。在许多此类场景中，聊天机器人会在提示词中被输入敏感的个人信息，作为上下文学习的样本、从数据库检索的记录或对话的一部分。提示词中提供的信息可能直接出现在输出中，若其中包含敏感信息，可能会引发隐私问题。因此，本文旨在探究这些模型在推理过程中的输入复制和复现能力，以及如何基于模型对HIPAA和GDPR等法规的内部知识，直接指示模型遵守这些法规以限制此类复制。更具体地说，我们发现当提示ChatGPT总结100名候选人的求职信时，它会在57.4%的案例中逐字保留个人身份信息（PII），并且我们发现基于性别认同等属性，这种保留在不同人群子群体间是不均匀的。随后，我们通过直接指示ChatGPT提供合规输出来探究其对隐私相关政策和隐私化机制的感知，并观察到输出中PII的显著省略。
英文摘要：
LLM-powered chatbots are becoming widely adopted in applications such as healthcare, personal assistants, industry hiring decisions, etc. In many of these cases, chatbots are fed sensitive, personal information in their prompts, as samples for in-context learning, retrieved records from a database, or as part of the conversation. The information provided in the prompt could directly appear in the output, which might have privacy ramifications if there is sensitive information there. As such, in this paper, we aim to understand the input copying and regurgitation capabilities of these models during inference and how they can be directly instructed to limit this copying by complying with regulations such as HIPAA and GDPR, based on their internal knowledge of them. More specifically, we find that when ChatGPT is prompted to summarize cover letters of a 100 candidates, it would retain personally identifiable information (PII) verbatim in 57.4% of cases, and we find this retention to be non-uniform between different subgroups of people, based on attributes such as gender identity. We then probe ChatGPT's perception of privacy-related policies and privatization mechanisms by directly instructing it to provide compliant outputs and observe a significant omission of PII from output.
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。
