Preserving Location Privacy in Ride-Hailing Service.

Ride-hailing service has become part of our daily life due to its convenience and low cost. However, it also raises location privacy concerns for riders, because the service provider can observe the full mobility traces of riders while they hail rides. To address this problem, we first present a baseline privacy preserving solution. Although the baseline solution can provide personalized rider location privacy, we identify potential location inference attacks against it. To overcome these attacks, we propose an enhanced privacy preserving solution that exploits novel obfuscation techniques to enable matching ride requests to drivers without breaching riders' location privacy and with limited loss of matching accuracy. We use real dataset of taxicabs to show that our solution, compared to previous work, provides much better ride matching, i.e., ride matching closer to the optimal solution, while preserving personalized riders' location privacy.