用锚点编码保护位置隐私，兼顾检索效果与安全。
Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs
- 用锚点+方向/距离分箱替代原始坐标，实现结构化隐私保护。
- 攻击者定位误差达370-400米，检索准确率仍保持超50%。
- 适合需要地理隐私的智能导航、位置推理类RAG应用。
本文提出PAS——隐私锚点替换机制，用于空间检索增强生成（Spatial RAG）系统中的用户位置隐私保护。不同于直接扰动坐标的传统差分隐私方法，PAS采用由锚点、方向分箱和距离分箱构成的相对锚点编码，可无缝集成至现代RAG流程。在合成城市数据集上的评估显示，PAS实现约370-400米的对抗性定位误差，同时保留超过50%的基线检索性能。尽管检索性能略有下降，下游生成质量仍具鲁棒性，表明大语言模型能补偿空间检索不完整。此外，实验发现PAS的隐私-效用关系非单调，归因于锚点离散化带来的几何偏差，区别于连续噪声机制（如geo-indistinguishability）。结果表明，结构化空间表示为RAG中的位置推理提供了实用的隐私方案。
原文摘要 · Abstract (English)
This work introduces PAS -- Privacy Anchor Substitution, a structured mechanism for enabling user location privacy in spatial retrieval-augmented generation (RAG) systems. Unlike conventional differential privacy methods that directly perturb user locations, PAS represents location with relative anchor encoding consisting of an anchor, direction bin, and distance bin, allowing seamless integration with modern RAG pipelines. We evaluate PAS on a synthetic urban dataset and show that it achieves impressive coarse privacy guarantees, with approximately 370-400m adversarial location error, while retaining more than half of the baseline retrieval performance. Despite the slight drop in retrieval performance, the downstream generation quality under PAS remains comparatively robust, indicating that large language models can compensate for imperfect spatial retrieval. Furthermore, we provide empirical analysis showing that PAS exhibits non-monotonic privacy-utility relationship with respect to privacy parameters. We attribute this to geometric bias induced by anchor discretization, making it different from continuous noise mechanisms such as geo-indistinguishability. Our results show that structured spatial representations offer a practical approach to privacy in location based reasoning in RAG systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。