A Stacked CNN-BiLSTM Model with Majority Technique for Detecting the Intrusions in Network
Keywords:
intrusion detection, stacked CNN-biLSTM, SMOTE, NSL-KDD, UNSW-NB15Abstract
The Internet of today is composed of almost 500,000 distinct networks. It is a challenging process to identify the attacks in every network connection according to the sorts of attacks they use since various attacks may have different connections, & the no. of attacks may range anywhere from a few to hundreds of network connections. Using a DNN (Deep Neural Network) technique to identify unknown attack packages is the primary objective of this research study. This will be accomplished by using an advanced Intrusion Detection System (IDS) that has excellent network performance. To conduct the assessment of metrics, UNSW-NB15 & NSL-KDD datasets are employed. This model makes use of LSTM & CNN to provide more accurate forecasts by concentrating more intently on the features of a successful earthquake. Initially, to reduce the quantity of noise in the majority group, we employ the One-Side Selection (OSS) technique. Then, to broaden the diversity of our samples, we employ the Synthetic Minority Oversampling Technique (SMOTE). This method of creating a balanced dataset dramatically reduces the amount of time required for training the model while allowing it to fully understand the characteristics of minority samples. Next, we use stacked CNN-biLSTM to extract spatial and temporal features, and then we use this information to build a deep stacked network model, which we stacked on top of one another. This proposed model can achieve remarkable accuracy in both datasets leaving a gap that is discussed at the end of the paper.
Downloads
References
I. T. Union, “Internet Security Threat Report,” 2019. [Online]. Available: http://linkinghub.elsevier.com/retrieve/pii/S1353485805001947.
S. B. Casey Cane, “33 Alarming Cybercrime Statistics You Should Know in 2019,” 2019. [Online]. Available: https://securityboulevard.com/2019/11/33-alarming-cybercrime-statistics-you-should-know-in-2019/.
H. J. Liao, C. H. Richard Lin, Y. C. Lin, and K. Y. Tung, “Intrusion detection system: A comprehensive review,” Journal of Network and Computer Applications. 2013, doi: 10.1016/j.jnca.2012.09.004.
H. Liu and H. Motoda, Feature Selection for Knowledge Discovery and Data Mining. 1998.
R. Prasad and V. Rohokale, “Artificial Intelligence and Machine Learning in Cyber Security,” 2020.
J. Lew et al., “Analyzing Machine Learning Workloads Using a Detailed GPU Simulator,” 2019, doi: 10.1109/ISPASS.2019.00028.
M. M. Najafabadi, F. Villanustre, T. M. Khoshgoftaar, N. Seliya, R. Wald, and E. Muharemagic, “Deep learning applications and challenges in big data analytics,” J. Big Data, 2015, doi: 10.1186/s40537-014-0007-7.
B. Dong and X. Wang, “Comparison deep learning method to traditional methods using for network intrusion detection,” 2016, doi: 10.1109/ICCSN.2016.7586590.
W. M. Jacob NM, “A Review of Intrusion Detection Systems,” Glob J Comput Sci Technol., vol. 17, no. 3, pp. 54–83, 2017, doi: 10.4018/978-1-5225-8176-5.ch003.
V. Jyothsna, V. V. Rama Prasad, and K. Munivara Prasad, “A Review of Anomaly based Intrusion Detection Systems,” Int. J. Comput. Appl., 2011, doi: 10.5120/3399-4730.
J. Sen and S. Mehtab, “Machine Learning Applications in Misuse and Anomaly Detection,” in Security and Privacy From a Legal, Ethical, and Technical Perspective, 2020.
A. L’Heureux, K. Grolinger, H. F. Elyamany, and M. A. M. Capretz, “Machine Learning with Big Data: Challenges and Approaches,” IEEE Access, 2017, doi: 10.1109/ACCESS.2017.2696365.
A. Jović, K. Brkić, and N. Bogunović, “A review of feature selection methods with applications,” 2015, doi: 10.1109/MIPRO.2015.7160458.
O. Saini and S. Sharma, “A Review on Dimension Reduction Techniques in Data Mining,” Comput. Eng. Intell. Syst., vol. 9, no. 1, pp. 7–14, 2018.
A. A. Megantara and T. Ahmad, “A hybrid machine learning method for increasing the performance of network intrusion detection systems,” J. Big Data, 2021, doi: 10.1186/s40537-021-00531-w.
Y. Zhou, G. Cheng, S. Jiang, and M. Dai, “Building an efficient intrusion detection system based on feature selection and ensemble classifier,” Comput. Networks, 2020, doi: 10.1016/j.comnet.2020.107247.
M. Nasser Mohammed and M. Mohamed Ahmed, “Data Preparation and Reduction Technique in Intrusion Detection Systems: ANOVA-PCA,” Int. J. Comput. Sci. Secur., 2019.
N. A. Awad, “Enhancing network intrusion detection model using machine learning algorithms,” Comput. Mater. Contin., 2021, doi: 10.32604/cmc.2021.014307.
M. Sarhan, S. Layeghy, and M. Portmann, “Evaluating Standard Feature Sets Towards Increased Generalisability and Explainability of ML-based Network Intrusion Detection,” 2021.
N. Moustafa and J. Slay, “UNSW-NB15: A comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set),” 2015, doi: 10.1109/MilCIS.2015.7348942.
I. Abrar, Z. Ayub, F. Masoodi, and A. M. Bamhdi, “A Machine Learning Approach for Intrusion Detection System on NSL-KDD Dataset,” 2020, doi: 10.1109/ICOSEC49089.2020.9215232.
Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,” IEEE Trans. Neural Networks Learn. Syst., 2021, doi: 10.1109/tnnls.2021.3084827.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.