Blockchain-oriented approach for detecting cyber-attack transactions

Financial Innovation

Table 10 Result on Identity theft

Category	Algorithm	Train			Test
Category	Algorithm	Precision	Recall	F1 score	Precision	Recall	F1 score
SML	XGB	0.962 ± 0.038	0.571 ± 0.000	0.717 ± 0.011	0.829 ± 0.060	0.529 ± 0.059	0.641 ± 0.026
	RF	1.000 ± 0.000	0.893 ± 0.012	0.943 ± 0.007	0.867 ± 0.049	0.588 ± 0.059	0.701 ± 0.058
	LGBM	1.000 ± 0.000	0.798 ± 0.036	0.887 ± 0.022	0.787 ± 0.059	0.559 ± 0.088	0.652 ± 0.081
UML	CBLOF	0.672 ± 0.032	0.427 ± 0.037	0.522 ± 0.037	0.583 ± 0.083	0.382 ± 0.088	0.461 ± 0.091
	HBOS	0.809 ± 0.017	0.463 ± 0.000	0.589 ± 0.005	0.739 ± 0.039	0.412 ± 0.088	0.528 ± 0.010
	KNN	0.790 ± 0.016	0.598 ± 0.012	0.681 ± 0.014	0.767 ± 0.033	0.676 ± 0.000	0.719 ± 0.031
	Avg KNN	0.877 ± 0.049	0.598 ± 0.012	0.711 ± 0.025	0.828 ± 0.095	0.676 ± 0.029	0.744 ± 0.056
	LOF	0.477 ± 0.023	0.134 ± 0.012	0.209 ± 0.017	0.325 ± 0.075	0.088 ± 0.029	0.139 ± 0.043
	OCSVM	0.732 ± 0.008	0.500 ± 0.012	0.594 ± 0.006	0.683 ± 0.017	0.441 ± 0.029	0.535 ± 0.017
	FB	0.407 ± 0.037	0.268 ± 0.024	0.324 ± 0.029	0.391 ± 0.083	0.382 ± 0.029	0.383 ± 0.117
	DeepSVDD	0.642 ± 0.051	0.268 ± 0.049	0.373 ± 0.040	0.647 ± 0.186	0.324 ± 0.147	0.417 ± 0.017
	VAE	0.719 ± 0.005	0.500 ± 0.012	0.590 ± 0.010	0.714 ± 0.014	0.441 ± 0.029	0.545 ± 0.026
	IF	0.794 ± 0.027	0.561 ± 0.000	0.657 ± 0.009	0.829 ± 0.094	0.598 ± 0.029	0.692 ± 0.025
	EIF	0.763 ± 0.049	0.622 ± 0.012	0.685 ± 0.027	0.764 ± 0.054	0.659 ± 0.000	0.707 ± 0.023
	WEIF	0.819 ± 0.063	0.744 ± 0.012	0.778 ± 0.022	0.814 ± 0.109	0.706 ± 0.029	0.753 ± 0.047