Deep Learning for Secure Mobile Edge Computing in Cyber-Physical Transportation Systems

MEC is able to be used to execute the compute-intensive applications on the edge of transportation networks directly. As a result, the communications traffic is substantially increased among the connected edge devices. Therewith, communications security is emerging as a serious problem, and as an important research issue of the communications security, active feature learning is studied in this article for actively detecting unknown attacks. A model based on deep learning is designed to learn attack features. This model uses unsupervised learning to accomplish the active learning process. In the evaluation, 10 datasets are used to conduct experiments. We compare our model with four other machine-learning-based algorithms, and the comparative results illustrate that our model has a 6 percent gain in accuracy.