Privacy-Preserving Compressive Sensing for Real-Time Traffic Monitoring in Urban City

Abstract

Traffic monitoring is a crucial means to solve traffic problems by collecting vehicular datain an urban road network. However, the leakage of sensitive data increases the risk of attackers spying on drivers’ privacy. To achieve real-time traffic monitoring without leaking data privacy, we propose a privacy-preserving compressive sensing (PPCS) mechanism to timely achieve the entire road network traffic conditions and design a series of feasible and securecomputation protocols to accelerate the speed of data processing. Specifically, we utilize the cloud to extract the spatial-temporal correlation between different road segments and compute a small number of road segments’ traffic congestion rates. Notably, we adopt compressivesensing (CS) technology to estimate other unknown road segments’ traffic conditions based onseveral known values. Besides, a comprehensive security analysis indicates that the PPCS proposed can protect vehicular data from being disclosed. Finally, we validate the effectiveness and efficiency of the mechanism through simulated experiments of computational costs and communication overhead.