“…Other areas where RNNs have been successful include deep learning [98], smart network management [14,31,36,37,40], emergency management and cyberphysical systems [42,43], the dynamic management of Cloud and Fog services [21,22,90], the use of machine learning in smart search [75,76] and network routing including the use of Software Defined Networks [5,19,20,29,30,38,91]. The CNN has also been successfully used in many fields [1,58], including for Magnetic Resonance Image reconstruction [94], automatic road segmentation [57], music generation [93] and relation extraction from plain text [45]. This wide usage and success of both the RNN and the CNN in a variety of applications justifies their use for Software Vulnerability Prediction in this paper, where text data processing and dimensionality reduction is carried out with a small CNN, and the RNN is used as a model that bonds both parts of the analysis.…”