Saved in:
Bibliographic Details
Main Authors: Guépin, Florent, Cisse, Cheick Tidiani, Renaud, Denis, Bidet, François, Legendre, Arnaud
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.10647
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914554203602944
author Guépin, Florent
Cisse, Cheick Tidiani
Renaud, Denis
Bidet, François
Legendre, Arnaud
author_facet Guépin, Florent
Cisse, Cheick Tidiani
Renaud, Denis
Bidet, François
Legendre, Arnaud
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10647
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories
Guépin, Florent
Cisse, Cheick Tidiani
Renaud, Denis
Bidet, François
Legendre, Arnaud
Artificial Intelligence
Cryptography and Security
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.
title diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories
topic Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2605.10647