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

TL;DR

This paper introduces a new framework for evaluating the utility of synthetic human mobility data and highlights the challenges in assessing privacy, proposing a novel membership inference attack for certain generative models.

Contribution

It presents a utility evaluation framework for synthetic trajectory generators and demonstrates privacy vulnerabilities through a new membership inference attack.

Findings

The utility evaluation framework helps assess synthetic data usefulness.

Privacy evaluation remains challenging and requires adversarial approaches.

A new membership inference attack exposes vulnerabilities in some generative models.

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.