Illegal vehicle parking is a common urban problem faced by major cities in the world, as it incurs tra c jams, which lead to air pollution and tra c accidents. Traditional approaches to detect illegal parking events rely highly on active human e orts. However, these approaches are extremely ine ective to cover a large city. The massive and high quality sharing bike trajectories from Mobike o er us with a unique opportunity to design a ubiquitous illegal parking detection system, as most of the illegal parking events happen at curbsides and have signi cant impact on the bike users. Two main components are employed in the proposed illegal parking detection system: 1) trajectory pre-processing, which lters outlier GPS points, performs map-matching and builds trajectory indexes; and 2) illegal parking detection, which models the normal trajectories, extracts features from the evaluation trajectories and utilizes a distribution test-based method to discover the illegal parking events. The system is deployed on the cloud, and used by Mobike internally. Finally, extensive experiments and many insightful case studies are presented.