ENHANCING INTRUSION DETECTION SYSTEM PERFORMANCE WITH 1D-CNN AND BI -LSTM COMBINATION
Main Article Content
Abstract
Due to the ever-increasing network traffic, the demand for a system that contain Network Intrusion Detection systems have increased as cloud technology usage has become widespread. Recent research has shown that deep learning models are effective for a variety of applications involving natural language processing on a critical part of Network Intrusion Detection such as anomaly detection. The architecture of a deep learning model has two layers: a pattern-matching layer and a fully linked layer for training the label of attack. In this study, we use a deep learning model with a modified architecture that integrates pattern matching with convolutional neural networks (CNN) and bidirectional long short-term memories (Bi-LSTM). The results show that CNN and Bi-LSTM can classify attack categories in the UNSW-NB15 dataset with an accuracy of 82%.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
Sinha, J., & Manollas, M. (2020, June). Efficient Deep CNN-BiLSTM Model for Network
Intrusion Detection. AIPR, Pages 223–231. 10.1145/3430199.3430224
A, A. H., & Sundarakantham, K. (2019). MACHINE LEARNING BASED INTRUSION
DETECTION SYSTEM. International Conference on Trends in Electronics and Informatics,
(3). 10.1109/icoei.2019.8862784
Chandre, P., Mahalle, P., & Shinde, G. (2022, June). Intrusion prevention system using
convolutional neural network for wireless sensor network. IAES International Journal of
Artificial Intelligence, Vol. 11, No. 2, pp. 504~515. 10.11591/ijai.v11.i2.pp504-515
LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553 (2015):
-444.
JIANG, K., WANG, W., WANG, A., & WU, H. (2020). Network Intrusion Detection
Combined Hybrid Sampling With Deep Hierarchical Network. IEEE Access, vol. 8,, pp.
-32476. 10.1109/ACCESS.2020.2973730
Shende, S., & Thorat, S. (2020, June). Long Short-Term Memory (LSTM) Deep Learning
Method for Intrusion Detection in Network Security. International Journal of Engineering
Research & Technology, Vol. 9(Issue 06). 10.17577/IJERTV9IS061016
Krishnan, A., & Mithra, S. T. (2021, June). A Modified 1D-CNN Based Network Intrusion
Detection System. IJRESM, vol. 4, no. 6, pp. 291–294.
http://journals.resaim.com/ijresm/article/view/921
Wang, Z., Yan, Y., & Oates, T. (2017). Time series classification from scratch with deep neural
networks: A strong baseline. Proceedings of the 2017 ACM on Conference on Information
and Knowledge Management, 765-774.
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving Deep into Rectifiers: Surpassing HumanLevel Performance on ImageNet Classification. (arXiv). 10.48550/ARXIV.1502.01852
Sinha, J., & Manollas, M. (2020, June). Efficient Deep CNN-BiLSTM Model for Network
Intrusion Detection. AIPR, Pages 223–231. 10.1145/3430199.3430224
Laghrissi, F. E., Douzi, S., Douzi, K., & Hssina, B. (2021, May 07). Intrusion detection
systems using long short-term memory (LSTM). Journal of Big Data, Vol. 8, No. 65.