Ride-hailing service has become a popular means of transportation due to its convenience and low cost.However,it also raises privacy concerns.Since riders’mobility information including the pick-up and drop-off locat...Ride-hailing service has become a popular means of transportation due to its convenience and low cost.However,it also raises privacy concerns.Since riders’mobility information including the pick-up and drop-off location is tracked,the service provider can infer sensitive information about the riders such as where they live and work.To address these concerns,we propose location privacy preserving techniques that efficiently match riders and drivers while preserving riders’location privacy.We first propose a baseline solution that allows a rider to select the driver who is the closest to his pick-up location.However,with some side information,the service provider can launch location inference attacks.To overcome these attacks,we propose an enhanced scheme that allows a rider to specify his privacy preference.Novel techniques are designed to preserve rider’s personalized privacy with limited loss of matching accuracy.Through trace-driven simulations,we compare our enhanced privacy preserving solution to existing work.Evaluation results show that our solution provides much better ride matching results that are close to the optimal solution,while preserving personalized location privacy for riders.展开更多
文摘Ride-hailing service has become a popular means of transportation due to its convenience and low cost.However,it also raises privacy concerns.Since riders’mobility information including the pick-up and drop-off location is tracked,the service provider can infer sensitive information about the riders such as where they live and work.To address these concerns,we propose location privacy preserving techniques that efficiently match riders and drivers while preserving riders’location privacy.We first propose a baseline solution that allows a rider to select the driver who is the closest to his pick-up location.However,with some side information,the service provider can launch location inference attacks.To overcome these attacks,we propose an enhanced scheme that allows a rider to specify his privacy preference.Novel techniques are designed to preserve rider’s personalized privacy with limited loss of matching accuracy.Through trace-driven simulations,we compare our enhanced privacy preserving solution to existing work.Evaluation results show that our solution provides much better ride matching results that are close to the optimal solution,while preserving personalized location privacy for riders.
