| Autor: |
Singh, Malvika, Mehtre, BM, Sangeetha, S |
| Předmět: |
|
| Zdroj: |
Multimedia Tools & Applications; Jul2022, Vol. 81 Issue 16, p22953-22983, 31p |
| Abstrakt: |
Insider threats are a significant source of security breaches in organizations. They are often identified using machine and deep learning methods. These methods rely on predefined rules, require explicit feature engineering, and also give rise to more false positives. To overcome these limitations, the proposed work focus on introducing an enhanced insider threat detection method based on user behavior analysis. It leads to fewer false positives, faster threat detection, and significantly higher classifier accuracy. This enhancement is achieved due to: use of data pre-processing steps for removal of noise; use of isometric feature mapping to minimize information loss while extracting the features from a high dimensional space; use of content based features to enhance the feature set for final classification; use of emperor penguin algorithm due to its effective exploitation and exploration for optimum feature selection; and, use of multi fuzzy classifier to parallelly handle variety of features for fast processing. The proposed method is tested on CMU-CERT v4.2 dataset using eight different performance evaluation metrics. Our test results show that the proposed method outperforms the existing methods. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink