For the performance evaluation, we mainly use the AUC (Area under the ROC Curve) in the Receiver Operating Characteristic (ROC) curve. Area Under Curve (AUC) is defined as the area under the ROC curve, and the value range is generally between 0.5 and 1. TPR@FPR=1E-2, 5E-3, 1E-3 will be used as a secondary reference only if needed, e.g. AUC metric can't distinguish the rankings. Please refer to [1].
Note:
True Positive Rate (TPR): TPR = TP/(TP+FN)
False Positive Rate (FPR): FPR = FP/(FP+TN)
TP: The attacks are recognized as the attacks;
TN: The real samples are recognized as the real ones;
FP: The real samples are recognized as the attacks;
FN: The attacks are recognized as the real samples;


[1] Aghajan, H., Augusto, J. C., & Delgado, R. L. C. (Eds.). (2009). Human-centric interfaces for ambient intelligence. Academic Press.