Modelo de Machine Learning para mitigar los fraudes informáticos de phishing basados en la ingeniería social en la Facultad de Ingeniería en Sistemas Electrónica e Industrial

Abstract

Nowadays, Phishing websites continue to be a significant threat in the vast cyberspace of the internet. When a user visits a Phishing URL, attackers obtain the user's personal and confidential information. Cyber criminals use various social engineering techniques to carry out identity theft or launch targeted attacks. Students and professors are not exempt from the strong influence of different social engineering techniques. Phishers seek ways to harm and make money through the manipulation and extortion of unsuspecting users. To address this problem, the present curricular integration work proposes implementing a Machine Learning model for Phishing detection deployed as a browser extension. 24 characteristics of its structure were extracted for the analysis of URLs and construction of the dataset. A comparison was made between various classification models such as Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (RNA), and K-Nearest Neighbors (KNN) to choose the most appropriate and best fit for the problem. Once the algorithms of the different training models were analyzed, the model used to classify URLs is an artificial neural network (RNA) achieving an accuracy of 99.98%. The purpose of this work is to help the FISEI community. The extension will mitigate and prevent users from becoming victims of malicious activities such as falling into Phishing URLs that apply various principles of Social Engineering.