Exploratory Analysis of Network Traffic in the Generation and Evaluation of Adversarial Samples

• Grant number: 25/09593-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2025
• End date: May 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Michele Nogueira Lima
• Grantee: Mateus Silva Jesué
• Host Institution: Instituto de Ciências Exatas (ICEx). Universidade Federal de Minas Gerais (UFMG). Ministério da Educação (Brasil). Belo Horizonte , SP, Brazil
• Associated research grant: 18/23098-0 - MENTORED: from modeling to experimentation - predicting and detecting DDoS and zero-day attacks, AP.TEM

Abstract

The use of machine learning techniques has become increasingly popular in the context of cybersecurity, being employed to enhance network security and mitigate the impact of potential attacks. However, artificial intelligence models are also being used to sophisticate attacks, one approach being the generation of adversarial samples and the training of models with them. This raises the need to study adversarial samples in comparison to original ones and to understand their impact. Therefore, this proposal aims to investigate the effects of adversarial samples on machine learning models, assess the vulnerabilities these samples introduce, and compare the statistical variations between adversarial and original samples-thus contributing to advancements in the field of cybersecurity. (AU)