Lightweight Intrusion Detection Model of the Internet of Things with Hybrid Cloud-Fog Computing

Table 7

Experimental results on ToN-IoT and BoT-IoT datasets.

Dataset	Model	Accuracy	Precision	Recall	F1-score	FAR	AUC
TON-IoT	RF [33]	0.9933	—	0.9980	0.99	0.0122	0.9929
	DFF [33]	0.9380	—	0.9229	0.94	0.0449	0.9782
	TP2SF [17]	0.9884	0.9723	0.9403	0.9528	—	—
	Sp2f [18]	0.9977	0.9990	0.9940	0.9964	—	—
	ConvNeXt	0.9996	0.9997	0.9980	0.9989	0.0001	0.9998
	Proposed model	0.9998	0.9997	0.9987	0.9992	0.0000	0.9989
BoT-IoT	RF [33]	0.9824	—	0.9824	0.99	0.0153	0.9836
	DFF [33]	0.9601	—	0.9599	0.98	0.0120	0.9907
	TP2SF [17]	0.9999	0.9997	0.9492	0.9708	—	—
	Sp2f [18]	0.9998	0.9994	0.9946	0.9987	—	—
	ConvNeXt	1.0000	0.9960	0.9923	0.9941	0.0000	1.0000
	Proposed model	1.0000	0.9962	1.0000	0.9981	0.0000	1.0000

The bold value in the table means that the corresponding model is optimal on this performance metric.