Personalized 3D Spatiotemporal Trajectory Privacy Protection with Differential and Distortion Geo-Perturbation

2025-11-27

AI Summary

Privacy leakage risks in 3D spatiotemporal trajectories arise from strong spatiotemporal correlations and altitude information. Method: This paper proposes 3DSTPM, a personalized privacy protection mechanism that integrates 3D geo-indistinguishability with distortion privacy to establish a synergistic framework; it introduces a novel Windowed Adaptive Privacy Budget Allocation (W-APBA) strategy—leveraging predictive accuracy and sensitivity—to dynamically allocate privacy budgets, and employs the Permute-and-Flip perturbation mechanism for adaptive location obfuscation. Contribution/Results: Experiments demonstrate that 3DSTPM effectively satisfies heterogeneous user privacy requirements while significantly reducing Quality-of-Service (QoS) degradation. It achieves superior trade-offs between privacy protection strength and localization service quality compared to state-of-the-art approaches.

Technology Category

• Machine Learning: Privacy
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Distributed Search

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

The rapid advancement of location-based services (LBSs) in three-dimensional (3D) domains, such as smart cities and intelligent transportation, has raised concerns over 3D spatiotemporal trajectory privacy protection. However, existing research has not fully addressed the risk of attackers exploiting the spatiotemporal correlation of 3D spatiotemporal trajectories and the impact of height information, both of which can potentially lead to significant privacy leakage. To address these issues, this paper proposes a personalized 3D spatiotemporal trajectory privacy protection mechanism, named 3DSTPM. First, we analyze the characteristics of attackers that exploit spatiotemporal correlations between locations in a trajectory and present the attack model. Next, we exploit the complementary characteristics of 3D geo-indistinguishability (3D-GI) and distortion privacy to find a protection location set (PLS) that obscures the real location for all possible locations. To address the issue of privacy accumulation caused by continuous trajectory queries, we propose a Window-based Adaptive Privacy Budget Allocation (W-APBA), which dynamically allocates privacy budgets to all locations in the current PLS based on their predictability and sensitivity. Finally, we perturb the real location using the allocated privacy budget by the PF (Permute-and-Flip) mechanism, effectively balancing privacy protection and Quality of Service (QoS). Simulation results demonstrate that the proposed 3DSTPM effectively reduces QoS loss while meeting the user's personalized privacy protection needs.

Problem

• Addresses privacy risks from spatiotemporal correlation in 3D trajectories.
• Mitigates privacy leakage due to height information in location data.
• Reduces QoS loss while meeting personalized privacy protection needs.

Innovation

• Personalized 3D trajectory protection with differential and distortion geo-perturbation
• Window-based adaptive privacy budget allocation for continuous queries
• PF mechanism balancing privacy and service quality via location perturbation