An empirical evaluation of Machine Learning for hardening security devices in Data Networks

The present paper has looked for applying Machine Learning techniques to analyze and classify network traffic from a security perspective, traffic like email, web, malware hashes and flood attacks have been analyzed resembling ICAP protocol architecture, the machine learning models have been trained and tested by using public Datasets and traffic obtained from active security devices, also several models have been proven obtaining high accuracy with them, leading to the conclusion that personalized security engines based on ML can be used to process malware and threatening traffic in Data Networks, as well as to improve the process of hardening on network devices.