Security, Trust, and Privacy for the Internet of Vehicles: A Deep Learning Approach
Ghulam Muhammad, Musaed Alhussein
Abstract
Intelligent sensing plays an important part in making our use of vehicles safe and problem-free. On average, a person spends over 35 hours in traffic jams each year. This valuable time could be saved by intelligent routing and real-time traffic alerts. Transport is a necessity of life, both in our everyday lives and at work. Navigation apps are now enabling users to access real-time alerts and alternatives. However, with the increase in the number of Internet-of-Vehicle-Things (IoVT), a large amount of data is produced within a short period of time. The huge data produced by the IoVT could be used to obtain greater perspective and to make dramatically smarter decisions. With this data, there is always a risk to security, trust, and privacy (STP). A standardized protocol is needed to preserve privacy and maintain the security of data. This paper addressed several STP issues in an intelligent transportation system. In addition, a deep learning model is proposed to process data generated by the IoVT.