Deep Autoencoders and Feedforward Networks Based on a New Regularization for Anomaly Detection

Table 4

Comparison of the proposed models’ results with existing methods on the NSL-KDD dataset.

Model	Accuracy	FPR	TPR	Precision	F-score
Proposed FFN	96.7	0.64	95.86	88.2	90.96
Proposed VAE	97.01	0.83	95.42	87.9	91.3
Two-stage ensemble [34]	85.79	11.7	86.8	88.0	—
DBN [33]	80.58	19.42	80.58	—	84.08
S-NDAE	85.42	14.58	85.42	—	87.37
SVM [38]			86.22		89.30
Ensemble			90.45		93.91
Multilayer			91.98		94.36
DBN + SVM	—	—	92.17	—	94.65
STL-IDS [36]	80.48	—	76.56	—	79.07

All the models in the same cell belong to the same reference.