Open access
2026
On the Adaptation of Trajectory Generative Models to Enforce Differential Privacy Through Gradient Perturbation
This paper investigates whether state-of-the-art deep learning trajectory generators can be adapted to satisfy differential privacy (DP) while retaining usable utility, and introduces RouteMIA, the first closed-box membership inference attack tailored to synthetic trajectories.
Víctor Rubio-Jornet, Javier Parra-Arnau, Jordi Forné
· IEEE Access · 0 citations