About intrusion detection system with machine learning: study of the application of boosting and the MINAS algorithm in performance improvement

• Grant number: 21/10320-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2021
• End date: February 28, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Kelton Augusto Pontara da Costa
• Grantee: Inaê Soares de Figueiredo
• Host Institution: Faculdade de Ciências (FC). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil

Abstract

Since its inception, the use of the internet has not stopped growing. According to data from the International Telecommunication Union, it is estimated that in 2019 around 51% of the world's population had access to the internet, reaching 93% of the people in certain countries, according to data from the same source. With the COVID-19 pandemic, there was a drastic change, with almost all service sectors migrating to the digital environment quickly and sometimes without the necessary preparation. Considering the number of people currently connected through the internet and the main purpose of the network as being to transmit data between points attached to it, there is a particular urgency in investing in more and better protection systems that can protect this data against cyber-attacks and also protect networks and computers from malicious intruders. In the last two years, several scientific publications have been published on the subject, proposing the application of different machine learning methods in search of the best system for detecting anomalies and intrusions in computer networks. This research project highlights the system developed by Dawoud et al. in 2020. It proposes to reproduce it and seeks to improve its performance by applying it in the structure proposed by the MINAS algorithm, in addition to complementing it with boosting techniques. (AU)