Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs

• URL: http://arxiv.org/abs/2605.05459v1
• Date: Wed, 06 May 2026 21:33:43 GMT
• Title: Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs
• Abstract summary: PAS represents location with relative anchor encoding consisting of an anchor, direction bin, and distance bin.<n>We evaluate PAS on a synthetic urban dataset and show that it achieves impressive coarse privacy guarantees, with approximately 370-400m adversarial location error.
• Score: 5.928512439824825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Towards Personalized Differentially Private Learning for Decentralized Local Graphs [62.244412935520025]
  Local Differential Privacy (LDP) has emerged as a promising solution for privacy-preserving data collection without relying on trusted servers.<n>Existing LDP-based graph learning methods typically assume uniform privacy requirements across users.<n>We propose PPGNN, a personalized differentially private framework for decentralized graph data.
  arXiv  Detail & Related papers  (2026-07-06T08:07:48Z)
• REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling [56.888597798431704]
  Open-World Object Detection (OWOD) requires detectors to identify previously unseen objects as unknown and incrementally incorporate them into the set of known categories.<n>Existing frameworks rely heavily on exemplar replay to mitigate catastrophic forgetting, but in some real applications, storing raw data conflicts with data access restrictions and leads to data exposure risks.<n>We propose REAL-OW, a novel rehearsal-free framework that decouples incremental knowledge through a collaborative adapter architecture.
  arXiv  Detail & Related papers  (2026-07-03T06:38:54Z)
• Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning [21.950552296952623]
  Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes.<n>A common defense involves per-example $ell$ clipping before prototype to bound sensitivity, followed by isotropic noise to enforce Local Differential Privacy.<n>We propose VPDR, a client-side privacy plug-in that seamlessly integrates into existing ProtoPFL.
  arXiv  Detail & Related papers  (2026-04-30T13:20:51Z)
• Differentially Private Manifold Denoising [5.0794787043927725]
  We introduce a differentially private manifold denoising framework that allows users to exploit sensitive reference datasets to correct noisy, non-private query points.<n>The framework performs rigorous privacy accounting across iterations and queries using $(varepsilon,)$-differential privacy (DP)<n> Practically, this framework brings differential privacy to manifold methods, retaining sufficient geometric signal for downstream tasks such as embedding, clustering, and visualization.
  arXiv  Detail & Related papers  (2026-04-01T14:13:59Z)
• CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras [16.147944008359957]
  CityGuard is a topology-aware transformer for privacy-preserving identity retrieval in decentralized surveillance.<n>A dispersion-adaptive metric learner adjusts instance-level margins according to feature spread, increasing intra-class compactness.<n>Private embedding maps are coupled with compact approximate indexes to support secure and cost-efficient deployment.
  arXiv  Detail & Related papers  (2026-02-20T08:00:17Z)
• Personalized 3D Spatiotemporal Trajectory Privacy Protection with Differential and Distortion Geo-Perturbation [64.60694805725727]
  This paper proposes a personalized 3Dtemporal trajectory privacy protection mechanism named 3DSTPM.<n>We analyze the characteristics of attackers that exploit correlations between locations in a trajectory and present the attack model.<n>Results demonstrate that the proposed 3DSTPM effectively reduces loss while meeting the user's personalized privacy protection needs.
  arXiv  Detail & Related papers  (2025-11-27T07:41:14Z)
• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• Signal Recovery from Random Dot-Product Graphs Under Local Differential Privacy [0.6906005491572401]
  We consider the problem of recovering latent information from graphs under $varepsilon$-edge local differential privacy.<n>For the class of generalized random dot-product graphs, we show that a standard local differential privacy mechanism induces a specific geometric distortion in the latent positions.<n>We show that consistent recovery of the latent positions is achievable by appropriately adjusting the statistical inference procedure for the privatized graph.
  arXiv  Detail & Related papers  (2025-04-24T06:02:02Z)
• Protecting Personalized Trajectory with Differential Privacy under Temporal Correlations [37.88484505367802]
  This paper proposes a personalized trajectory privacy protection mechanism (PTPPM) We identify a protection location set (PLS) for each location by employing the Hilbert curve-based minimum distance search algorithm. We put forth a novel Permute-and-Flip mechanism for location perturbation, which maps its initial application in data publishing privacy protection to a location perturbation mechanism.
  arXiv  Detail & Related papers  (2024-01-20T12:59:08Z)
• Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks [72.51255282371805]
  We prove a privacy bound for the KL divergence between model distributions on worst-case neighboring datasets. We find that this KL privacy bound is largely determined by the expected squared gradient norm relative to model parameters during training.
  arXiv  Detail & Related papers  (2023-10-31T16:13:22Z)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• Graph-Homomorphic Perturbations for Private Decentralized Learning [64.26238893241322]
  Local exchange of estimates allows inference of data based on private data. perturbations chosen independently at every agent, resulting in a significant performance loss. We propose an alternative scheme, which constructs perturbations according to a particular nullspace condition, allowing them to be invisible.
  arXiv  Detail & Related papers  (2020-10-23T10:35:35Z)
• PGLP: Customizable and Rigorous Location Privacy through Policy Graph [68.3736286350014]
  We propose a new location privacy notion called PGLP, which provides a rich interface to release private locations with customizable and rigorous privacy guarantee. Specifically, we formalize a user's location privacy requirements using a textitlocation policy graph, which is expressive and customizable. Third, we design a private location trace release framework that pipelines the detection of location exposure, policy graph repair, and private trajectory release with customizable and rigorous location privacy.
  arXiv  Detail & Related papers  (2020-05-04T04:25:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.