A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities

2026-04-21

AI Summary

Preserving privacy while maintaining data utility in synthetic human mobility trajectory generation—and accurately assessing the privacy risks of existing models—remains an open challenge. This work proposes a dual-perspective analytical framework: it establishes a systematic evaluation protocol for trajectory utility and introduces adversarial membership inference attacks to quantitatively measure privacy leakage risks in generative models. The study reveals, for the first time, that certain generative models widely assumed to be resilient against trajectory linkage attacks remain significantly vulnerable to membership inference attacks. This finding challenges prevailing assumptions about their security guarantees and underscores the limitations of current privacy evaluation mechanisms.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Generation
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Human mobility data are used in numerous applications, ranging from public health to urban planning. Human mobility is inherently sensitive, as it can contain information such as religious beliefs and political affiliations. Historically, it has been proposed to modify the information using techniques such as aggregation, obfuscation, or noise addition, to adequately protect privacy and eliminate concerns. As these methods come at a great cost in utility, new methods leveraging development in generative models, were introduced. The extent to which such methods answer the privacy-utility trade-off remains an open problem. In this paper, we introduced a first step towards solving it, by the introduction and application of a new framework for utility evaluation. Furthermore, we provide evidence that privacy evaluation remains a great challenge to consider and that it should be tackled through adversarial evaluation in accordance with the current EU regulation. We propose a new membership inference attack against a subcategory of generative models, even though this subcategory was deemed private due to its resistance over the trajectory user-linking problem.

Problem

• synthetic trajectory
• privacy-utility trade-off
• generative models
• membership inference attack
• human mobility data

Innovation

• synthetic trajectory generation
• utility evaluation framework
• membership inference attack
• privacy-utility trade-off
• adversarial privacy evaluation