How is the performance of classification algorithms for DDoS detection in CICIDS2017 typically measured?

Performance is typically measured using metrics that account for the imbalanced nature of the data. These include Accuracy, Precision, Recall (Sensitivity), F1-Score, Specificity, Receiver Operating Characteristic (ROC) curve with Area Under the Curve (AUC), and the Confusion Matrix. Precision and Recall are particularly important for identifying attack instances correctly.