CICIDS2018
The 2018 Intrusion Detection System Evaluation Dataset released by the Canadian Institute for Cybersecurity (CIC), containing network traffic data from multiple realistic attack scenarios. It is a widely used benchmark dataset in the network security research community.
Timeline (last 90 days)
The study was based on the CICIDS2018 dataset, used a CNN classifier, and employed stratified 5-fold cross-validation.
The Top3 configuration achieved an accuracy of 97.148%, a weighted F1 of 97.055%, and an MCC of 0.9675, comprehensively outperforming the Full21 configuration using all 21 metrics (accuracy 95.999%, weighted F1 95.521%, MCC 0.9549).
All Facts (2)
The study was based on the CICIDS2018 dataset, used a CNN classifier, and employed stratified 5-fold cross-validation.
50%UnverifiedThe Top3 configuration achieved an accuracy of 97.148%, a weighted F1 of 97.055%, and an MCC of 0.9675, comprehensively outperforming the Full21 configuration using all 21 metrics (accuracy 95.999%, weighted F1 95.521%, MCC 0.9549).
50%