Projects · MSc thesis · UPF
Privacy-preserving synthetic mobility data
Can deep generative models produce mobility data that's both useful and private? A user-level privacy–utility evaluation on real GPS trips.
Python · PyTorch · VAE · WGAN-GP · Membership inference
Why
Wider access to mobility data would advance urban planning and transport modelling, but it’s rarely shared: a few weeks of someone’s trips reveal where they live, where they work and their routine.

Synthetic data promises a way out: train a generative model on the real trips, then release trips it generates instead. Whether that delivers utility and privacy together is still unclear, because most earlier work looked at tabular data, or at privacy for individual records rather than for whole people.
The dataset
The GeoLife GPS dataset from Beijing, processed into 7,739 origin–destination trips from 154 users. Travel follows the city’s rhythm: commuting peaks on weekday mornings and early evenings, and very little happens overnight.
What it is
My MSc thesis at Universitat Pompeu Fabra. It asks three questions of synthetic trips generated from that data:
- Utility: how faithfully does the synthetic data reproduce real mobility?
- Privacy: can a user-level membership inference attack tell which people were in the training data?
- Activity: are more active users, with more trips to learn from, more exposed?
Experiment setup
Two deep generative models, built in PyTorch, are compared against a bootstrap baseline:

- Variational autoencoder (VAE): compresses each trip into a latent space and decodes samples back into trips.
- Wasserstein GAN with gradient penalty (WGAN-GP): a generator learns to produce trips that a critic can’t tell apart from real ones.
- Bootstrap: resamples real trips directly. It’s a positive control: if the attack can’t catch the bootstrap, it can’t catch anything.
Utility

Both models reproduced the temporal structure of travel well, but the spatial structure poorly. On a downstream prediction task, a model trained on synthetic trips and tested on real ones recovered only about a quarter of real-data performance (TSTR ratio 0.25–0.27).
Privacy evaluation

The attack works at the level of people, not individual trips: for each evaluation user, it predicts whether their trips were used to train the generator.
- VAE and WGAN-GP: no measurable membership leakage (AUC ≈ 0.50, chance level).
- Bootstrap: clear leakage (AUC 0.75), confirming the attack works when there’s something to find.
- Activity level: no membership difference could be established across activity levels, but direct copying of real records rose with user activity across all models.

What it means

The privacy observed here is largely a by-product of under-fitting, not evidence of a favourable trade-off: the models protected people by not learning enough to be useful. Establishing rigorously where privacy and utility can coexist is the foundation for releasing synthetic mobility data with confidence, and for the open access that mobility research depends on.

Presented at Urban Transitions 2026
I presented this work as an oral talk at Urban Transitions 2026 (10–12 November, Sitges, Spain).



