Location Privacy Protection Method for Networked Vehicles Based on K-Means and Shamir

In recent years, the rapid development of vehicular networking technology has brought convenience to intelligent transportation systems, while also increasing the risk of data privacy leakage based on location services. To address this issue, this paper proposes a privacy protection framework named KSAL. Firstly, KSAL utilizes the K-Means algorithm to cluster vehicle location information. By dividing vehicle locations into multiple clusters, specific vehicle locations can be effectively concealed, preventing attackers from accurately tracking them. This clustering method not only protects the privacy of vehicle locations but also enhances the efficiency and security of vehicular networking systems. Secondly, KSAL introduces the Shamir algorithm to protect the privacy and security of server response location data. This algorithm divides response data into multiple secret shares and distributes these shares to different vehicles within the same cluster. Only when a sufficient number of secret shares are collected can the complete response data be reconstructed. This method effectively prevents attackers from eavesdropping on and tampering with server responses to service requests, thereby protecting the privacy and security of the data. Comprehensive experimental results demonstrate that this method not only prevents attackers from tracking vehicle location information but also effectively prevents the theft and tampering of server response location data.