cs.LG提交于 2026-10-22已译

通用 LLM 时代正在忽视情境化隐私

Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs

Prakhar Ganesh · Yash More · Marco Romanelli · Ferdinando Fioretto · Golnoosh Farnadi

中文摘要

随着大语言模型(LLM)的应用范围与能力持续增长，隐私问题日益突出。用户日益频繁地在多种不同情境中与同一个通用系统交互，因此容易倾向于采用“一刀切”的隐私方案。然而，这忽视了隐私研究数十年来的一项关键认识：隐私本质上是情境化的。论文指出，提示隐私(prompt privacy)现有研究正转向构建统一框架，这种做法具有严重误导性，并可能营造虚假的安全感。即使未来研究继续沿此方向，也必须处理提示隐私各项理想属性之间的根本张力。因此，有必要重新审视统一框架。建议沿三条关键路径推进：针对具体应用部署 LLM、针对具体情境评估隐私框架，以及提升隐私素养。

关键要点

01现有通用隐私方案忽略隐私的情境依赖性。
02统一提示隐私框架可能误导研究并制造安全感。
03未来方案需权衡提示隐私多项理想属性之间的张力。
04建议面向具体应用部署 LLM，并按情境评估隐私框架。
05提升用户隐私素养也是关键改进方向。

解读

尚无解读。

原始英文摘要

arXiv:2610.29925v1 Announce Type: new Abstract: As large language models (LLMs) continue to grow in scope and capability, privacy concerns are on the rise. Since users increasingly interact with a single general-purpose system across many distinct contexts, there is a natural tendency to pursue a one-size-fits-all solution to privacy. Unfortunately, this overlooks a crucial insight from decades of privacy research: privacy is inherently contextual. In this paper, we argue that existing work in prompt privacy is drifting towards attempts to design a unified framework, which is highly misleading and can foster a false sense of security. Furthermore, we argue that even future work in this direction needs to wrestle with fundamental tensions across various desirable properties of prompt privacy. Thus, such continued attempts towards a unified framework need to be reconsidered. We recommend three critical paths forward: application-specific deployment of LLMs, context-specific evaluation of privacy frameworks, and better privacy literacy.