File(s) under permanent embargo
Anomaly Detection Using XGBoost Ensemble of Deep Neural Network Models
journal contribution
posted on 2023-10-23, 23:35 authored by S T Ikram, A K Cherukuri, B Poorva, P S Ushasree, Chris ZhangChris Zhang, X Liu, Gang LiGang LiIntrusion Detection Systems (IDSs) utilise deep learning techniques to identify intrusions with maximum accuracy and reduce false alarm rates. The feature extraction is also automated in these techniques. In this paper, an ensemble of different Deep Neural Network (DNN) models like MultiLayer Perceptron (MLP), BackPropagation Network (BPN) and Long Short Term Memory (LSTM) are stacked to build a robust anomaly detection model. The performance of the ensemble model is analysed on different datasets, namely UNSW-NB15 and a campus generated dataset named VIT SPARC20. Other types of traffic, namely unencrypted normal traffic, normal encrypted traffic, encrypted and unencrypted malicious traffic, are captured in the VIT SPARC20 dataset. Encrypted normal and malicious traffic of VIT SPARC20 is categorised by the deep learning models without decrypting its contents, thus preserving the confidentiality and integrity of the data transmitted. XGBoost integrates the results of each deep learning model to achieve higher accuracy. From experimental analysis, it is inferred that UNSW NB results in a maximal accuracy of 99.5%. The performance of VIT_SPARC20 in terms of accuracy, precision and recall are 99.4%. 98% and 97%, respectively.
History
Journal
Cybernetics and Information TechnologiesVolume
21Pagination
175 - 188Publisher DOI
ISSN
1314-4081eISSN
1314-4081Publication classification
C1 Refereed article in a scholarly journalUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC