A Sequential Approach to Network Intrusion Detection


Lee, Nicholas Ming Ze and Pang, Ying Han and Ooi, Shih Yin (2020) A Sequential Approach to Network Intrusion Detection. In: Computational Science and Technology. Lecture Notes in Electrical Engineering (Computational Science and Technology), 603 . Springer Verlag, pp. 11-21. ISBN 9789811500572

[img] Text
10.1007@978-981-15-0058-9.pdf - Published Version
Restricted to Repository staff only

Download (46MB)


In this paper, we combine the sequential modeling capability of Recurrent Neural Network (RNN), and the robustness of Random Forest (RF) in detecting network intrusions. Past events are modelled by RNN, capturing informative and sequential properties for the classifier. With the new output vectors being incorporated into the input features, RF is exacted to consider high-level sequential representation when selecting the best candidate to split. The proposed approach is tested and compared on the UNSW-NB15 data set, demonstrating its competence with encouraging results, and achieving an optimal trade-off between detection and false positive rate.

Item Type: Book Section
Uncontrolled Keywords: Neural networks (Computer science), Network-based Intrusion, Detection System, Machine Learning, Random Forest, Recurrent Neural Network
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 16 Dec 2020 10:40
Last Modified: 16 Dec 2020 10:40
URII: http://shdl.mmu.edu.my/id/eprint/7944


Downloads per month over past year

View ItemEdit (login required)