Safe TD3 for Personalized Spatiotemporal Trajectory Privacy Protection
IEEE Transactions on Mobile Computing · 2026-08 · 25 (8) · 12908-12922
DOI: 10.1109/tmc.2026.3674518 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-08. Verfasst von Minghui Min und 7 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Jiangsu Province Young Scientific and Technological Talent Support Program.
Abstract (Originalsprache)
With the widespread adoption of location-based services (LBS), user-generated trajectory data shows strong spatiotemporal correlation, rendering it highly vulnerable to inference attacks that expose sensitive information. In particular, once semantic locations like “hospital” and “bank” are identified, the risk of trajectory leakage increases substantially. To address this issue, this paper formulates a personalized spatiotemporal trajectory privacy protection framework, which is designed to protect locations with varying semantic sensitivities on the trajectory from the attacker with spatiotemporal correlation information. We model the trajectory privacy protection problem as a Markov Decision Process (MDP) and introduce the reinforcement learning (RL) technique to adjust the privacy parameters dynamically. Specifically, we leverage the twin delayed deep deterministic policy gradient (TD3) algorithm to enhance the stability and accuracy of policy evaluation, enabling efficient learning of optimal policies in continuous action spaces. Furthermore, a safe exploration strategy is incorporated to continuously evaluate and avoid high-risk state-action pairs, thereby enhancing privacy protection. Simulation results demonstrate that the proposed mechanism significantly improves privacy protection while effectively reducing Quality of Service (QoS) loss, exhibiting better convergence and overall system utility.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Jiangsu Province Young Scientific and Technological Talent Support Program
- National Science Foundation
- Seatrium New Energy Laboratory, Singapore Ministry of Education (MOE) Tier 1
- Nanyang Technological University Centre for Computational Technologies in Finance
- Research Innovation and Enterprise (RIE) 2025 Industry Alignment Fund-Industry Collaboration Projects
- Agency for Science, Technology and Research
Zitieren
APA
Min, M., Dai, M., Ye, J., Li, S., Zhang, H., Pan, M., Niyato, D., & Han, Z. (2026). Safe TD3 for Personalized Spatiotemporal Trajectory Privacy Protection. IEEE Transactions on Mobile Computing, 25(8), 12908-12922. https://doi.org/10.1109/tmc.2026.3674518
Vancouver
Min M, Dai M, Ye J, Li S, Zhang H, Pan M, et al. Safe TD3 for Personalized Spatiotemporal Trajectory Privacy Protection. IEEE Transactions on Mobile Computing. 2026;25(8):12908-12922. doi:10.1109/tmc.2026.3674518
BibTeX
@article{Min2026,
author = {Min, Minghui and Dai, Minghui and Ye, Jun and Li, Shiyin and Zhang, Hongliang and Pan, Miao and Niyato, Dusit and Han, Zhu},
title = {Safe TD3 for Personalized Spatiotemporal Trajectory Privacy Protection},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {8},
pages = {12908--12922},
doi = {10.1109/tmc.2026.3674518}
}
EUVIMED