Use of ensemble techniques in machine learning to detect scanning in computer networks

• Grant number: 19/01597-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): June 01, 2019
• Effective date (End): December 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Kelton Augusto Pontara da Costa
• Grantee: Gabriel Vieira Ferreira
• Host Institution: Faculdade de Ciências (FC). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil

Abstract

Many organizations experience attacks that compromise the security of their information, which happens through vulnerabilities in systems. As a result, there has been an expansion in the network security market, companies responsible for testing and analyzing systems to detect vulnerabilities and inhibit them against possible attacks. There are several programs that take advantage of the vulnerabilities present in a computer system, causing damage to organizations, theft of information, among many other harms. Some of these programs are called exploits. The main tool of manipulation and application of exploits is called Metasploit. The ease of handling and the amount of online tutorials available for this tool makes it a weapon in the hands of malicious individuals, resulting in the need for exploit detection techniques for organizations to have a crucial value in protecting their data. The present scientific initiation proposal intends to analyze recent techniques and tools to detect exploits, as well as to implement a new technique through the Ensemble method, this being very usual in Machine Learning and for the said context.