We use cookies to improve your experience with our site.
Yubin Duan, Guo-Ju Gao, Ming-Jun Xiao, Jie Wu. Cloaking Region Based Passenger Privacy Protection in Ride-Hailing Systems[J]. Journal of Computer Science and Technology, 2020, 35(3): 629-646. DOI: 10.1007/s11390-020-0256-1
Citation: Yubin Duan, Guo-Ju Gao, Ming-Jun Xiao, Jie Wu. Cloaking Region Based Passenger Privacy Protection in Ride-Hailing Systems[J]. Journal of Computer Science and Technology, 2020, 35(3): 629-646. DOI: 10.1007/s11390-020-0256-1

Cloaking Region Based Passenger Privacy Protection in Ride-Hailing Systems

  • With the quick development of the sharing economy, ride-hailing services have been increasingly popular worldwide. Although the service provides convenience for users, one concern from the public is whether the location privacy of passengers would be protected. Service providers (SPs) such as Didi and Uber need to acquire passenger and driver locations before they could successfully dispatch passenger orders. To protect passengers’ privacy based on their requirements, we propose a cloaking region based order dispatch scheme. In our scheme, a passenger sends the SP a cloaking region in which his/her actual location is not distinguishable. The trade-off of the enhanced privacy is the loss of social welfare, i.e., the increase in the overall pick-up distance. To optimize our scheme, we propose to maximize the social welfare under passengers’ privacy requirements. We investigate a bipartite matching based approach. A theoretical bound on the matching performance under specific privacy requirements is shown. Besides passengers’ privacy, we allow drivers to set up their maximum pick-up distance in our extended scheme. The extended scheme could be applied when the number of drivers exceeds the number of passengers. Nevertheless, the global matching based scheme does not consider the interest of each individual passenger. The passengers with low privacy requirements may be matched with drivers far from them. To this end, a pricing scheme including three strategies is proposed to make up for the individual loss by allocating discounts on their riding fares. Extensive experiments on both real-world and synthetic datasets show the efficiency of our scheme.
  • loading

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return