Privacy-focused model generates realistic car energy data from fewer variables
PRISMA: Differentially Private Synthetic In-Car Telemetry via Differentiable Simulation
Cryptography and Security
Summary
Creating synthetic car energy use data while protecting individual privacy is difficult because the data is very detailed. The authors show that the essential information can be captured with just a few key variables and public map data like elevation. They developed PRISMA, a method that compresses detailed energy consumption into a simple format, applies privacy protections to this simplified data, and then reconstructs detailed data using physics-based simulation without risking privacy. This approach keeps the synthetic data diverse and realistic even under strong privacy guarantees.
What this means in practice
- •For automotive data engineers: Create synthetic in-car energy datasets that maintain privacy while preserving realistic driving patterns for testing and development.
- •For urban planners: Use private synthetic vehicle energy profiles combined with public map data to study energy impacts of traffic without exposing sensitive driver information.
Authors
Kilian Zeiseweis, Nele Sophie Brügge, Marven Kummerfeldt, Ali Raza, Esfandiar Mohammadi
Abstract
Differentially private synthesis of in-car energy consumption data is challenging because the output is high-dimensional, and known lower bounds show that the privacy-utility trade-off degrades with the square root of the number of output dimensions. However, we observe that the intrinsic dimensionality of in-car energy consumption is much lower than that of the raw trace: given a small set of contextual personal variables-such as start point, end point, the car model, and the driving behavior-the consumption profile can be largely explained by publicly available map data (including elevation) combined with a physical model of vehicle energy use. We exploit this low intrinsic dimensionality in PRISMA, a Privacy-preserving In-car Synthesis and Modelling Algorithm. PRISMA involves three stages: (i) energy consumption traces are encoded into a low-dimensional latent space; (ii) the distribution of latent vectors is synthesized using the differentially private tabular data synthesis algorithm AIM, and (iii) samples drawn from this distribution are decoded back into full energy consumption traces via a differentiable physics-based simulation, a step that consumes no additional privacy budget since it uses only public information. By using a compact, physically-grounded latent representation of the traces, PRISMA significantly reduces the effective output dimension. Our experimental results show that PRISMA achieves for a competitive $\varepsilon = 0.5$ a better data synthesis performance than prior tabular and marginal-based DP synthesis baselines by preserving the diversity of the original power consumption profiles without collapsing to a small set of modes.