Smart vehicles produce large amounts of data, much of which is sensitive and at risk of privacy breaches. As attackers increasingly exploit anonymised metadata within these datasets to profile drivers, it’s important to find solutions that mitigate this information leakage without hindering innovation and ongoing research. Synthetic data has emerged as a promising tool to address these privacy concerns, as it allows for the replication of real-world data relationships while minimising the risk of revealing sensitive information. In this paper, we examine the use of synthetic data to tackle these challenges. We start by proposing a comprehensive taxonomy of 14 in-vehicle sensors, identifying potential attacks and categorising their vulnerability. We then focus on the most vulnerable signals, using the Passive Vehicular Sensor (PVS) dataset to generate synthetic data with a Tabular Variational Autoencoder (TVAE) model, which included over 1 million data points. Finally, we evaluate this against 3 core metrics: fidelity, utility, and privacy. Our results show that we achieved 90.1% statistical similarity and 78% classification accuracy when tested on its original intent, while also preventing the profiling of the driver.

This paper introduces an implementation of a Co-Evolutionary Selection Training (CEST) method for enhancing the efficiency of deep neural network training. Unlike models such as Generative Adversarial Networks (GANs), CEST adopts a distinct approach: it uses an evolutionary algorithm to select minimal subsets of challenging examples from the original dataset, rather than generating them through another network. This process employs a competitive predator–prey scheme, introducing an additional layer of complexity to the training dynamics. The proposed method is thoroughly studied and validated, demonstrating notable reductions in training timewith no compromise in accuracy.