发表机构
Indian Institute of Technology Kanpur; Université de Lorraine; CNRS; Inria; LORIA（印度理工学院坎普尔分校; 洛林大学; 法国国家科学研究中心; 法国国家信息与自动化研究所; 洛林计算机科学及其应用研究实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出用于隐私风险分析的人-LLM协同框架PRIAM，以CBDC福利方案为例验证，该框架通过人机迭代协作优化隐私风险评估，为相关领域提供基础贡献。
AI 中文摘要
基于央行数字货币（CBDC）的福利方案可能存在隐私侵入风险，因为它们会处理大量受益人个人数据，并引发监控、歧视和污名化等隐私危害。此类福利发放方案涉及复杂的数字生态系统和大量利益相关者，因此，对其隐私风险进行评估需要开展广泛的信息收集与综合、复杂推理、场景探索、情境评估以及人类判断，这为人-大语言模型（LLM）协同提供了理想场景，有效整合人类与LLM的互补能力可产生远超仅人类或仅LLM评估的结果。本文提出了首个用于系统隐私风险分析方法PRIAM的人-LLM协同框架，该框架规定了迭代协作流程：LLM处理大规模文献证据以生成初始输出，随后由人类专家对初始输出进行解读和评估，指导LLM进一步优化，并运用自身判断确定最终输出。我们以PRIAM的数据特征化活动为例，结合基于CBDC的福利方案用例对该框架进行说明，结果表明，尽管LLM会生成初始数据类别并为数据属性分配初始值，但人类专家会对其进行评估并提供反馈以优化，区分文献证据与推断结果、识别信息缺口，并标记无依据或模糊的输出。该框架为人-AI协同开展隐私风险评估提供了基础性贡献。
英文摘要
Central Bank Digital Currency (CBDC)-based welfare schemes may be potentially privacy invasive as they process significant volumes of beneficiary personal data and lead to privacy harms such as surveillance, discrimination and stigmatization. Such welfare delivery schemes involve complex digital ecosystems and large number of stakeholders. Consequently, to examine their privacy risks, privacy risk assessments require extensive information gathering and synthesis, complex reasoning, scenario explorations, contextual evaluation and human judgement. Thus, they present ideal scenarios for human-LLM teaming, where effective integration of complementary human and LLM capabilities can yield an outcome far superior to either human-only or LLM-only assessments. In this paper, we propose a first human-LLM teaming framework for the systematic privacy risk analysis methodology called PRIAM. The framework specifies an iterative collaborative process in which the LLM processes large-scale documentary evidence to produce initial outputs, which are then interpreted and evaluated by human experts who direct their further refinement by the LLM and exercise their judgement to finalize the output. We illustrate the framework on the data characterization activity of PRIAM using a CBDC-based welfare scheme use case. The illustration demonstrates that while LLMs generate the initial data categories and assign initial values to data attributes, human experts evaluate and provide feedback to refine them, distinguishing documented evidence from inferences, identifying information gaps, and flagging unsupported or ambiguous outputs. This framework serves as a foundational contribution towards human-AI teaming for privacy risk assessments.
Comments10 pages
