Evaluating Variant Deep Learning and Machine Learning Approaches for the Detection of Cyberattacks on the Next Generation 5G Systems
Borgesen, Michael E.
Kholidy, Hisham A.; Advisor
SUNY Polytechnic Institute
machine learning approaches , cyberattacks detection , 5G systems security , intrusion detection systems , performance evaluation , Naïve Bayes model , logistic regression model , decision tree model , random forest model
5G technology promises to completely transform telecommunication networks, introducing a wealth of benefits such as faster download speeds, lower download times, low latency, high network capacity. These benefits will pave the way for additional new capabilities and support connectivity for applications like smart homes and cities, industrial automation, autonomous vehicles, telemedicine, and virtual/augmented reality. However, attackers use these resources in their advantages to speed up the attacking process. This report evaluates four different machine learning and deep learning approaches namely the Naïve Bayes model, the logistic regression model, the decision tree model, and the random forest model. The performance evaluation and the validation of these approaches are discussed in details in this report.