LONG SHORT-TERM MEMORY DEEP LEARNING MODEL DETECTING DDOS ATTACKS
Main Article Content
Abstract
Recently, Distributed Denial of Service (DDoS) attack threats have become increasingly sophisticated, posing challenges to conventional defense systems. Early detection of attack signs is crucial to protect against and counter these attack threats. The research proposes using a model based on the Long Short-Term Memory (LSTM) deep learning technique to identify DDoS threats in network data packets. This LSTM technique includes selected algorithms and feature extraction, automatically updated during training. Even with a small amount of data, LSTM operates quickly and accurately. The study conducted experiments on the CICDDoS2019 dataset, with results showing the model achieving the following performance metrics: Accuracy reaching 93%, Precision at 96%, Recall reaching 93%, and F1 Score at 94%. The research aims to provide a model capable of processing sequential data and retaining long-term learned information. Integrating the model into network monitoring and security systems can enhance the ability to detect and respond to increasingly complex network attack threats.
Keywords
DdoS, Deep Learning, DoS, LSTM, Machine Learning
Article Details
References
Ahuja, N., Singal, G., Mukhopadhyay, D., & Kumar, N. (2021). Automated DDoS attack detection in software defined networking. Journal of Network and Computer Applications, 187, Article 103108.
Alzahrani, S., & Hong, L. (2018). Detection of distributed denial of service (DDoS) attacks using artificial intelligence on cloud. In 2018 IEEE World Congress on Services (SERVICES) (pp.35-36). San Francisco, CA.
Deepak Kumar, R. K. Pateriya, Rajeev Kumar Gupta, Vasudev Dehalwar, & Ashutosh Sharma (2019). Computer Science and Engineering Department, Maula-na Azad National Institute of Technology, Bhopal, India, 462003.
Dincalp. (2018). Anomaly based distributed denial of service attack detection and prevention with machine learning. In Proceedings of the 2nd Interna-tional Symposium on Multidisciplinary Studies and Innovative Technologies (pp.19-21, October 2018). Ankara, Turkey.
Divyang Dave, Meet Kava, R. K. Gupta, & Kaushal Shah. (2022). Deep Learning approach for Intrusion Detection System. IEEE International Conference on Technology, Research, and Innovation for Betterment of Society (TRIBES), 2022. https://doi.org/10.1109/TRIBES52498.2021.9751643
Doriguzzi-Corin, R., Millar, S., Scott-Hayward, S., Martinez-del-Rincon, J., & Siracusa, D. (2020). Lucid: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection. IEEE Transactions on Network and Service Management, 17(2), 876-889. https://doi.org/10.1109/TNSM.2020.2971776
Fadlil, A., Riadi, I., & Aji, S.(2017). Review of detection DDoS attack detection us-ing Naïve Bayes classifier for network forensics. Bulletin of Electrical Engineering and Informatics, 6,
140-148. https://www.unb.ca/cic/datasets/ddos-2019.html
University of New Brunswick. DDoS Evaluation Dataset (CIC-DDoS2019). (2021). Retrieved December 20, 2021, from https://www.unb.ca/cic/ da-tasets/ddos-2019.html
Setitra, M. A., Fan, M., Agbley, B. L., & Bensalem, Z. E. (2023). Optimized MLP-CNN model to enhance detecting DDoS attacks in SDN environment. Network, 3(4), 538-562.
Wang, C., Zheng, J., & Li, X. (2017). Research on DDoS attacks detection based on RDF-SVM. In Proceedings of the 10th International Conference on Intelli-gent Computation Technology and Automation (pp.9-12). Changsha, China.
Zahid Hasan, Md., Zubair Hasan, K. M., & Sattar, Abdus (2018). Burst header packet flood detection in optical burst switching network using deep learning model. Procedia Computer Science, 143, 970-977.
Zhu, M., Ye, K., & Xu, C. Z. (2018). Network anomaly detection and identification based on deep learning methods. In M. Luo, & L. J. Zhang (Eds.), Cloud Computing – CLOUD 2018. CLOUD 2018. Lecture Notes in Com-puter Science. Cham: Springer.