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 data sets and identifies modified GPS trajectories effectively and efficiently.