On the application of Explainable Artificial Intelligence (XAI) techniques for generating images from data packages to detect anomalies in computer networks

• Grant number: 21/05516-1
• Support Opportunities: Regular Research Grants
• Duration: February 01, 2022 - January 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Kelton Augusto Pontara da Costa
• Grantee: Kelton Augusto Pontara da Costa
• Host Institution: Faculdade de Ciências (FC). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil
• Associated researchers: João Paulo Papa ; Rafal Scherer

Abstract

The Internet, has brought higher complexity to the Network Management area. Detecting anomalies in a network with the highest efficiency and in the shortest possible time has been the goal of many researchers, which have used Artificial Intelligence. This project aims to convert network data into images so that Convolutional Neural Networks can be used to detect deviations in network behavior. The XAI models will bring explainability and clarity to the AI algorithms used, making it possible to understand the reasons for anomalous detection or not. (AU)