A Privacy-Preserving Solution for Intelligent Transportation Systems: Private Driver DNA

• Published in: IEEE transactions on intelligent transportation systems 2023-01, Vol.24 (1), p.258-273
• Main Authors: Costantino, Gianpiero, De Vincenzi, Marco, Martinelli, Fabio, Matteucci, Ilaria
• Format: Article
• Language: English
• Subjects: Attitudes; Authentication; Blockchains; Customization; Data loss; Data privacy; DNA; Driver behavior; driver DNA; homomorphic encryption; Intelligent transportation systems; ITS; Measurement; order revealing encryption; Privacy; Vehicles
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2022.3217358

The rising connection of vehicles with the road infrastructure enables the creation of data-driven applications to offer drivers customized services. At the same time, these opportunities require innovative solutions to protect the drivers' privacy in a complex environment like an Intelligent Transportation System (ITS). This need is even more relevant when data are used to retrieve personal behaviors or attitudes. In our work, we propose a privacy-preserving solution, called Private Driver DNA, which designs a possible architecture, allowing drivers of an ITS to receive customized services. The proposed solution is based on the concept of Driver DNA as characterization of driver's driving style. To assure privacy, we perform the operations directly on sanitized data, using the Order Revealing Encryption (ORE) method. Besides, the proposed solution is integrated with ITS architecture defined in the European project E-Corridor. The result is an effective privacy-preserving architecture for ITS to offer customized products, which can be used to address drivers' behaviors, for example, to environmental-friendly attitudes or a more safe driving style. We test Private Driver DNA using a synthetic dataset generated with the vehicle simulator CARLA. We compare ORE with another encryption method like Homomorphic Encryption (HE) and some other privacy-preserving schemas. Besides, we quantify privacy gain and data loss utility after the data sanitization process.