RE-Trace: Re-identification of Modified GPS Trajectories

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • University of Bonn
View graph of relations

Details

Original languageEnglish
Article number31
JournalACM Transactions on Spatial Algorithms and Systems
Volume10
Issue number4
Early online date5 Feb 2024
Publication statusPublished - 23 Oct 2024

Abstract

GPS trajectories are a critical asset for building spatio-temporal predictive models in urban regions in the context of road safety monitoring, traffic management, and mobility services. Currently, reliable and efficient data misuse detection methods for such personal, spatio-temporal data, particularly in data breach cases, are missing. This article addresses an essential aspect of data misuse detection, namely, the re-identification of leaked and potentially modified GPS trajectories. We present RE-Trace - a contrastive learning-based model that facilitates reliable and efficient re-identification of GPS trajectories and resists specific trajectory transformation attacks aimed to obscure a trajectory's origin. RE-Trace utilizes contrastive learning with a transformer-based trajectory encoder to create trajectory representations, robust to various trajectory modifications. We present a comprehensive threat model for GPS trajectory modifications and demonstrate the effectiveness and efficiency of the RE-Trace re-identification approach on three real-world datasets. Our evaluation results demonstrate that RE-Trace significantly outperforms state-of-the-art baselines on all datasets and identifies modified GPS trajectories effectively and efficiently.

Keywords

    contrastive learning, data privacy, GPS trajectories, personal data, spatio-temporal data

ASJC Scopus subject areas

Cite this

RE-Trace: Re-identification of Modified GPS Trajectories. / Schestakov, Stefan; Gottschalk, Simon; Funke, Thorben et al.
In: ACM Transactions on Spatial Algorithms and Systems, Vol. 10, No. 4, 31, 23.10.2024.

Research output: Contribution to journalArticleResearchpeer review

Schestakov, S, Gottschalk, S, Funke, T & Demidova, E 2024, 'RE-Trace: Re-identification of Modified GPS Trajectories', ACM Transactions on Spatial Algorithms and Systems, vol. 10, no. 4, 31. https://doi.org/10.1145/3643680
Schestakov, S., Gottschalk, S., Funke, T., & Demidova, E. (2024). RE-Trace: Re-identification of Modified GPS Trajectories. ACM Transactions on Spatial Algorithms and Systems, 10(4), Article 31. https://doi.org/10.1145/3643680
Schestakov S, Gottschalk S, Funke T, Demidova E. RE-Trace: Re-identification of Modified GPS Trajectories. ACM Transactions on Spatial Algorithms and Systems. 2024 Oct 23;10(4):31. Epub 2024 Feb 5. doi: 10.1145/3643680
Schestakov, Stefan ; Gottschalk, Simon ; Funke, Thorben et al. / RE-Trace : Re-identification of Modified GPS Trajectories. In: ACM Transactions on Spatial Algorithms and Systems. 2024 ; Vol. 10, No. 4.
Download
@article{71b54239a56b411990c54c4b12ff69b0,
title = "RE-Trace: Re-identification of Modified GPS Trajectories",
abstract = "GPS trajectories are a critical asset for building spatio-temporal predictive models in urban regions in the context of road safety monitoring, traffic management, and mobility services. Currently, reliable and efficient data misuse detection methods for such personal, spatio-temporal data, particularly in data breach cases, are missing. This article addresses an essential aspect of data misuse detection, namely, the re-identification of leaked and potentially modified GPS trajectories. We present RE-Trace - a contrastive learning-based model that facilitates reliable and efficient re-identification of GPS trajectories and resists specific trajectory transformation attacks aimed to obscure a trajectory's origin. RE-Trace utilizes contrastive learning with a transformer-based trajectory encoder to create trajectory representations, robust to various trajectory modifications. We present a comprehensive threat model for GPS trajectory modifications and demonstrate the effectiveness and efficiency of the RE-Trace re-identification approach on three real-world datasets. Our evaluation results demonstrate that RE-Trace significantly outperforms state-of-the-art baselines on all datasets and identifies modified GPS trajectories effectively and efficiently.",
keywords = "contrastive learning, data privacy, GPS trajectories, personal data, spatio-temporal data",
author = "Stefan Schestakov and Simon Gottschalk and Thorben Funke and Elena Demidova",
note = "Publisher Copyright: {\textcopyright} 2024 Copyright held by the owner/author(s).",
year = "2024",
month = oct,
day = "23",
doi = "10.1145/3643680",
language = "English",
volume = "10",
number = "4",

}

Download

TY - JOUR

T1 - RE-Trace

T2 - Re-identification of Modified GPS Trajectories

AU - Schestakov, Stefan

AU - Gottschalk, Simon

AU - Funke, Thorben

AU - Demidova, Elena

N1 - Publisher Copyright: © 2024 Copyright held by the owner/author(s).

PY - 2024/10/23

Y1 - 2024/10/23

N2 - GPS trajectories are a critical asset for building spatio-temporal predictive models in urban regions in the context of road safety monitoring, traffic management, and mobility services. Currently, reliable and efficient data misuse detection methods for such personal, spatio-temporal data, particularly in data breach cases, are missing. This article addresses an essential aspect of data misuse detection, namely, the re-identification of leaked and potentially modified GPS trajectories. We present RE-Trace - a contrastive learning-based model that facilitates reliable and efficient re-identification of GPS trajectories and resists specific trajectory transformation attacks aimed to obscure a trajectory's origin. RE-Trace utilizes contrastive learning with a transformer-based trajectory encoder to create trajectory representations, robust to various trajectory modifications. We present a comprehensive threat model for GPS trajectory modifications and demonstrate the effectiveness and efficiency of the RE-Trace re-identification approach on three real-world datasets. Our evaluation results demonstrate that RE-Trace significantly outperforms state-of-the-art baselines on all datasets and identifies modified GPS trajectories effectively and efficiently.

AB - GPS trajectories are a critical asset for building spatio-temporal predictive models in urban regions in the context of road safety monitoring, traffic management, and mobility services. Currently, reliable and efficient data misuse detection methods for such personal, spatio-temporal data, particularly in data breach cases, are missing. This article addresses an essential aspect of data misuse detection, namely, the re-identification of leaked and potentially modified GPS trajectories. We present RE-Trace - a contrastive learning-based model that facilitates reliable and efficient re-identification of GPS trajectories and resists specific trajectory transformation attacks aimed to obscure a trajectory's origin. RE-Trace utilizes contrastive learning with a transformer-based trajectory encoder to create trajectory representations, robust to various trajectory modifications. We present a comprehensive threat model for GPS trajectory modifications and demonstrate the effectiveness and efficiency of the RE-Trace re-identification approach on three real-world datasets. Our evaluation results demonstrate that RE-Trace significantly outperforms state-of-the-art baselines on all datasets and identifies modified GPS trajectories effectively and efficiently.

KW - contrastive learning

KW - data privacy

KW - GPS trajectories

KW - personal data

KW - spatio-temporal data

UR - http://www.scopus.com/inward/record.url?scp=85203093865&partnerID=8YFLogxK

U2 - 10.1145/3643680

DO - 10.1145/3643680

M3 - Article

AN - SCOPUS:85203093865

VL - 10

JO - ACM Transactions on Spatial Algorithms and Systems

JF - ACM Transactions on Spatial Algorithms and Systems

SN - 2374-0353

IS - 4

M1 - 31

ER -

By the same author(s)