EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Trajectory Data Publishing Scheme Based on Transformer Decoder and Differential Privacy

Haiyong Wang, Wei Huang

ISPRS International Journal of Geo-Information · 03.03.2026 · 15 (3) · 106

DOI: 10.3390/ijgi15030106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 03.03.2026. Verfasst von Haiyong Wang und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jiangsu Planned Projects for Postdoctoral Research Funds, Stable Supporting Fund of National Key Laboratory of Autonomous Marine Vehicle Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proliferation of Location-Based Services (LBSs) has generated vast trajectory datasets that offer immense analytical value but pose critical privacy risks. Achieving an optimal balance between data utility and privacy preservation remains a challenge, a difficulty compounded by the limitations of existing methods in modeling complex, long-term spatiotemporal dependencies. To address this, this paper proposes a trajectory data publishing scheme combining a Transformer decoder with differential privacy. Unlike traditional single-layer approaches, the proposed method establishes a systematic generation–generalization framework. First, a Transformer decoder is integrated into a Generative Adversarial Network (GAN). This architecture mitigates the gradient vanishing issues common in RNN-based models, generating high-fidelity synthetic trajectories that capture long-range correlations while decoupling them from sensitive source data. Second, to provide rigorous privacy guarantees, a clustering-based generalization strategy is implemented, utilizing Exponential and Laplace mechanisms to ensure ϵ-differential privacy. Experiments on the Geolife and Foursquare NYC datasets demonstrate that the scheme significantly outperforms leading baselines, achieving a superior trade-off between privacy protection and data utility.

Förderung

  • National Natural Science Foundation of China
  • Jiangsu Planned Projects for Postdoctoral Research Funds
  • Stable Supporting Fund of National Key Laboratory of Autonomous Marine Vehicle Technology
  • Jiangsu Province Postgraduate Research and Practice Innovation Program

Zitieren

APA

Wang, H., & Huang, W. (2026). Trajectory Data Publishing Scheme Based on Transformer Decoder and Differential Privacy. ISPRS International Journal of Geo-Information, 15(3), 106. https://doi.org/10.3390/ijgi15030106

Vancouver

Wang H, Huang W. Trajectory Data Publishing Scheme Based on Transformer Decoder and Differential Privacy. ISPRS International Journal of Geo-Information. 2026;15(3):106. doi:10.3390/ijgi15030106

BibTeX
@article{Wang2026,
  author = {Wang, Haiyong and Huang, Wei},
  title = {Trajectory Data Publishing Scheme Based on Transformer Decoder and Differential Privacy},
  journal = {ISPRS International Journal of Geo-Information},
  year = {2026},
  volume = {15},
  number = {3},
  pages = {106},
  doi = {10.3390/ijgi15030106}
}
Kostenlos starten →