Privacy Preserving Driving Style Recognition
This work addresses privacy issues in driving style recognition for insurance companies, but it appears incremental as it applies existing privacy-preserving methods to a specific domain.
The paper tackles the problem of predicting driving styles (aggressive or defensive) for insurance companies using vehicle data while addressing privacy concerns, presenting a technique that prevents both the company and drivers from learning private information, with experimental validation of its effectiveness and efficiency.
In order to better manage the premiums and encourage safe driving, many commercial insurance companies (e.g., Geico, Progressive) are providing options for their customers to install sensors on their vehicles which collect individual vehicle's traveling data. The driver's insurance is linked to his/her driving behavior. At the other end, through analyzing the historical traveling data from a large number of vehicles, the insurance company could build a classifier to predict a new driver's driving style: aggressive or defensive. However, collection of such vehicle traveling data explicitly breaches the drivers' personal privacy. To tackle such privacy concerns, this paper presents a privacy-preserving driving style recognition technique to securely predict aggressive and defensive drivers for the insurance company without compromising the privacy of all the participating parties. The insurance company cannot learn any private information from the vehicles, and vice-versa. Finally, the effectiveness and efficiency of the privacy-preserving driving style recognition technique are validated with experimental results.