PromptGraph：用于在大语言模型推理中平衡隐私与效用的图引导提示净化

中文摘要 AI 辅助

大语言模型（LLM）服务带来了基本的隐私挑战。敏感信息不仅可从显式标识符推断，还能从无害文本跨度间的上下文关联推断。现有净化器通常给单个跨度分配隐私或效用信号，未显式建模它们之间的成对关系。本文提出PromptGraph，一种用于隐私保护的LLM推理的图引导提示净化方法。PromptGraph在跨度级别估计隐私泄露以及跨度对之间与效用相关的上下文依赖关系。它将每个提示表示为一个属性图，节点携带跨度级别的隐私分数，边编码保留效用所需的上下文依赖关系。净化目标选择一个受保护的跨度集，在惩罚上下文依赖关系损失的同时最大化隐私增益。当上下文证据隐藏时，这种公式化明确地平衡了隐私和效用。受保护的跨度在本地进行净化，返回的占位符仅在通过本地一致性检查后才恢复。我们进行了广泛的实验，表明PromptGraph在隐私和效用之间实现了比提示隐私基线更有利的平衡。

英文摘要

Large Language Model (LLM) services introduce a fundamental privacy challenge. Sensitive information may be inferred not only from explicit identifiers, such as names or phone numbers, but also from contextual associations among otherwise innocuous spans. Existing sanitizers typically assign privacy or utility signals to individual spans without explicitly modeling pairwise relationships among them. In this paper, we propose PromptGraph, a graph-guided prompt-sanitization approach for privacy-preserving LLM inference. PromptGraph estimates privacy leakage at the span level and utility-relevant contextual dependencies between pairs of spans. It represents each prompt as an attributed graph, in which nodes carry span-level privacy scores and edges encode contextual dependencies needed to preserve utility. The sanitization objective selects a protected span set that maximizes privacy gain while penalizing the loss of contextual dependencies. This formulation explicitly balances privacy and utility when contextual evidence is hidden. Protected spans are sanitized locally, and returned placeholders are restored only after passing local consistency checks. We conduct extensive experiments showing that PromptGraph achieves a more favorable balance between privacy and utility than prompt-privacy baselines.

发表机构

• School of Computer Science and Information Engineering, Hefei University of Technology（计算机科学与信息工程学院，合肥工业大学）
• International College Beijing, China Agricultural University（北京国际学院，中国农业大学）

机构由 AI 辅助整理，请以论文原文为准。