[论文] Demystifying the Privacy-Utility Trade-off in LLM Interactions

论文概要

研究领域: cs.AI, cs.CR
作者: Zhenhua Liu, Zhanxu Xie, Junjie Yu, Tong Zhu, Lijun Li, Wenliang Chen
发布时间: 2026-09-13
arXiv: 2609.10992

中文摘要

大型语言模型融入日常任务依赖于上下文丰富的指令，不可避免地暴露敏感用户信息。当前的隐私保护方法通常采用与上下文无关的静态规则，导致严重的效用降级。然而，关于脱敏如何影响下游性能的具体机制在很大程度上尚未探索。为此，我们进行系统分析以解构隐私-效用权衡，揭示三个潜在机制：（1）上下文相关效用，揭示数据价值根据用户意图从关键约束转变为可丢弃噪声；（2）策略适应，规定删除和替换之间的选择取决于任务对事实完整性或结构连贯性的依赖；（3）组合交互，证明属性形成协同依赖或拮抗冗余的语义网络。基于这些见解，我们引入意图驱动的本地保护框架，通过提炼轻量级模型 Veilmind-4B 驱动动态提取-脱敏-恢复管道。

原文摘要

The integration of Large Language Models into daily tasks relies on context-rich instructions, inevitably exposing sensitive user information. Current privacy-preserving methods typically employ context-agnostic static rules, causing severe utility degradation. However, the specific mechanisms governing how sanitization impacts downstream performance remain largely underexplored. To address this, we conduct a systematic analysis to deconstruct the privacy-utility trade-off, uncovering three underlying mechanisms: (1) Context-Dependent Utility, which first establishes when to sanitize by revealing that data value shifts from critical约束 to dispensable noise based on user intent; (2) Strategic Adaptation, which subsequently determines how to sanitize by dictating that the choice between removal and replacement depends on the task's reliance on factual integrity versus structural coherence; and (3) Combinatorial Interplay, which finally extends the protection scope by demonstrating that attributes form a semantic web of synergistic dependencies or antagonistic redundancies. Guided by these insights, we introduce an intent-driven local protection framework. By distilling a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline, our approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines, advancing the privacy-utility trade-off toward the Pareto frontier.

自动采集于 2026-09-13

#论文 #arXiv #AI #小凯