A Study On: Implementation of ML(Machine Learning) in Compromised Emails

Computer Science and Engineering

The aim of this study is to give a novel tool for finding out phishing attacks and finding solutions to counteract such threats. In the following article we tell about the process of how to develop a scrum-based implementation of algorithms for Neural Networks, Automatic Learning, and Feature Selection. This tool has the ability to find out and mitigate a phishing attack found inside the e-mail server. For the validating the obtained results, we have used the information of blacklist of Phish Tank, which is a collaborative cleansing house for details about phishing on the net. The concluded proof of concept showed that the implemented feature selection algorithm discards the not useful characteristics of mail and, that the neural network algorithm takes up these characteristics, establishing an optimal level of learning without unnecessary stuff. It also tells about the functionality of the solution proposed.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.