Time efficiency on computational performance of PCA, FA and TSVD on ransomware detection
Ransomware is able to attack and take over access of the targeted user's computer. Then the hackers demand a ransom to restore the user's access rights. Ransomware detection process especially in big data has problems in term of computational processing time or detection speed. Thus, it re...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Advanced Engineering and Science
2022
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/98677/1/MohdYazidIdris2022_TimeEfficiencyonComputationalPerformance.pdf http://eprints.utm.my/id/eprint/98677/ http://dx.doi.org/10.52549/ijeei.v10i1.3481 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Malaysia |
| Language: | English |
| Summary: | Ransomware is able to attack and take over access of the targeted user's computer. Then the hackers demand a ransom to restore the user's access rights. Ransomware detection process especially in big data has problems in term of computational processing time or detection speed. Thus, it requires a dimensionality reduction method for computational process efficiency. This research work investigates the efficiency of three dimensionality reduction methods, i.e.: Principal Component Analysis (PCA), Factor Analysis (FA) and Truncated Singular Value Decomposition (TSVD). Experimental results on CICAndMal2017 dataset show that PCA is the fastest and most significant method in the computational process with average detection time of 34.33s. Furthermore, result of accuracy, precision and recall also show that the PCA is superior compared to FA and TSVD. |
|---|