Network security specialists use machine learning algorithms to detect computer network attacks and prevent unauthorized access to their networks. Traditionally, signature and anomaly detection techniques have been used for network defense. However, detection techniques must adapt to keep pace with continuously changing security attacks. Therefore, machine learning algorithms always learn from experience and are appropriate tools for this adaptation. In this paper, ten machine learning algorithms were trained with the KDD99 dataset with labels, then they were tested with different dataset without labels. The researchers investigate the speed and the efficiency of these machine learning algorithms in terms of several selected benchmarks such as time to build models, kappa statistic, root mean squared error, accuracy by attack class, and percentage of correctly classified instances of the classifier algorithms.


This is the online version published ahead of print. Initial submission: July 2017; revised submission: January 2018.