Trajectories are nowadays valuable information for a wide range of applications. However they are also inherently sensitive, as they contain highly personal information about individuals. Facing this challenge, synthesizing mobility trajectories has emerged as a promising solution to leverage mobility information while preserving privacy. State-of-the-art models, often rely on the false assumptions of generative models implicit privacy and fails to provide privacy guarantees while preserving trajectories utility. Here, we introduce diffGHOST, a conditional diffusion model based on latent space segmentation, designed to answer this challenge. Thus, this paper propose a methodology that identify and mitigate memorization of critical samples using condition segments of a learn latent space.
@article{arxiv.2605.10647,
title = {diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories},
author = {Florent Guépin and Cheick Tidiani Cisse and Denis Renaud and François Bidet and Arnaud Legendre},
journal= {arXiv preprint arXiv:2605.10647},
year = {2026}
}