Deep Learning Approaches for Predictive Masquerade Detection

Table 3

The structure of the used data configurations.

Characteristics		Data Configurations
		SEA	SEA 1v49	Greenberg Truncated	Greenberg Enriched	PU Truncated	PU Enriched
Number of users		50	50	50	50	8	8
Block Size		100	100	10	10	10	10
Number of blocks for every user	Training set	2500	50	100	100	150	150
	Test set	100	2526~2550	130	130	400	400
	Total	2600	2576~2600	230	230	550	550
Number of blocks for all users	Training set	125000	2500	5000	5000	1200	1200
	Test set	5000	127269	6500	6500	3200	3200
	Total	130000	129769	11500	11500	4400	4400
Distribution of the training set	Normal	2500	2500	5000	5000	1200	1200
	Masquerader	122500	0	0	0	0	0
	Total	125000	2500	5000	5000	1200	1200
Distribution of the test set	Normal	4769	4769	5000	5000	400	400
	Masquerader	231	122500	1500	1500	2800	2800
	Total	5000	127269	6500	6500	3200	3200