Tècniques basades en l'aprenentatge automàtic quàntic per a la detecció d'intrusions a la xarxa en xarxes definides per software
Year: 2024
Type: dissertation
Abstract: This work explores the application of Quantum Machine Learning (QML) algorithms for intrusion detection systems in software-defined networks, comparing their performance with classical machine learning methods. Using the UNR-IDD dataset, various QML models, including QKNN, QSVM, QNN, and HQNN, were evaluated and demonstrated promising results in terms of accuracy. The models were tested using quantum simulators, which allowed for an examination of their potential advantages, such as enhanced precision and efficiency in processing complex datasets. The findings suggest that QML holds considerable promise for improving intrusion detection systems, potentially offering significant benefits over classical approaches.
Author: Lo Anguera, Joan
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7112756902