Deep Learning Approaches for Predictive Masquerade Detection

Table 1

Best results of the related works.

Model	Dataset	Configuration	Hit (%)	FAR (%)
HMM	SEA	SEA	60	1
Naive Bayes	SEA	SEA	79	2
		SEA 1v49	62.8	4.6
	Greenberg	Greenberg Truncated	70.9	4.7
		Greenberg Enriched	82.1	5.7
Conditional Naive Bayes	SEA	SEA	84	8.8
		SEA 1v49	90.7	1
	Greenberg	Greenberg Enriched	84.13	9.4
	PU	PU Enriched	84	8
SVM	SEA	SEA	82.6	3
		SEA 1v49	94.8	0
	Greenberg	Greenberg Truncated	71.1	6
		Greenberg Enriched	87.3	6.4
	PU	PU Enriched	60	2
Tree-based	PU	PU Enriched	85	10