Attack Detection in Software-Defined Network Technology Data Using A Transformer-Based Convolutional Neural Network Model with An Archimedean Optimization Algorithm

Öz

Recently, there has been an increase in the number of people who do their daily work with the help of technological devices. During this time, the concept of the Internet of Things has emerged, where smart devices can communicate with each other. While all these developments make people's lives easier, on the other hand, they make it necessary to develop systems that can ensure secure transmission of data. In this study, a hybrid approach based on artificial intelligence was developed to detect attacks on software-defined network data. The dataset includes normal, denial of service, brute force, cross-site scripting and SQL injection network attacks. Archimedes optimization algorithm has been used as a preprocessing step in the proposed approach. Thanks to Archimedes optimization algorithm, the selection of efficient features in the dataset was done. Then, the dataset was trained using the transformer-based convolutional neural network model. The softmax method was used as a classifier for detecting normal or attack network traffic. The overall accuracy achieved in the experimental analysis of this study was 98.94%.

Anahtar Kelimeler

• Deep learning
• decision support system
• internet of things
• data security
• software defined network

Arşimet Optimizasyon Algoritması ile Trafo Tabanlı Evrişimsel Sinir Ağı Modelini Kullanarak Yazılım Tanımlı Ağ Teknolojisi Verilerinde Saldırı Tespiti

Öz

Son zamanlarda insanların teknoloji cihazları kullanarak günlük işlerini idame etmesindeki oran artmıştır. Akıllı cihazların birbirleriyle iletişim sağlayabildiği şu zamanda nesnelerin interneti kavramı ortaya çıkmıştır. Bütün bu gelişmeler insan hayatını daha da kolaylaştırırken diğer taraftan verilerin iletimini güvenli bir şekilde aktarılmasını sağlayabilen sistemlerin tasarlanmasını zorunlu hale getirmiştir. Bu çalışmada yazılım tanımlı ağ verilerinde saldırı tespitini gerçekleştirebilen yapay zekâ tabanlı hibrit bir yaklaşım geliştirilmiştir. Veri kümesi normal, dağıtılmış hizmet reddi, kaba kuvvet saldırıları, siteler arası betik çalıştırma ve SQL enjeksiyon ağ saldırı türlerini içermektedir. Önerilen yaklaşımda ön işlem adımı olarak Arşimet optimizasyon algoritması kullanılmıştır. Arşimet optimizasyon algoritması sayesinde veri kümesindeki verimli özelliklerin seçimi gerçekleştirilmiştir. Ardından trafo tabanlı evrişimsel sinir ağı modeli kullanılarak veri kümesi eğitilmiştir. Ağ trafiğinin normal veya saldırı tespitinde softmax yöntemi sınıflandırıcı olarak kullanılmıştır. Bu çalışmanın deneysel analizinde %98,94 genel doğruluk başarısı elde edilmiştir.

Anahtar Kelimeler

• Derin öğrenme
• karar destek sistemi
• nesnelerin interneti
• veri güvenliği
• yazılım tabanlı ağ

Kaynakça

1. [1] S.K. Tayyaba, M.A. Shah, O.A. Khan, A.W. Ahmed, Software Defined Network (SDN) Based Internet of Things (IoT), in: Proc. Int. Conf. Futur. Networks Distrib. Syst., ACM, New York, NY, USA, 2017: pp. 1–8. doi:10.1145/3102304.3102319.
2. [2] H. Polat, M. Turkoglu, O. Polat, Deep network approach with stacked sparse autoencoders in detection of DDoS attacks on SDN‐based VANET, IET Commun. 14 (2020) 4089–4100. doi:10.1049/iet-com.2020.0477.
3. [3] N. Ahuja, G. Singal, D. Mukhopadhyay, N. Kumar, Automated DDOS attack detection in software defined networking, J. Netw. Comput. Appl. 187 (2021) 103108. doi:10.1016/j.jnca.2021.103108.
4. [4] I. Haque, D. Saha, SoftIoT: A resource-aware SDN/NFV-based IoT network, J. Netw. Comput. Appl. 193 (2021) 103208. doi:10.1016/j.jnca.2021.103208.
5. [5] S. Javanmardi, M. Shojafar, R. Mohammadi, A. Nazari, V. Persico, A. Pescapè, FUPE: A security driven task scheduling approach for SDN-based IoT–Fog networks, J. Inf. Secur. Appl. 60 (2021) 102853. doi:10.1016/j.jisa.2021.102853.
6. [6] M.V.O. de Assis, L.F. Carvalho, J.J.P.C. Rodrigues, J. Lloret, M.L. Proença Jr, Near real-time security system applied to SDN environments in IoT networks using convolutional neural network, Comput. Electr. Eng. 86 (2020) 106738. doi:10.1016/j.compeleceng.2020.106738.
7. [7] B. Nugraha, R.N. Murthy, Deep Learning-based Slow DDoS Attack Detection in SDN-based Networks, in: 2020 IEEE Conf. Netw. Funct. Virtualization Softw. Defin. Networks, IEEE, 2020: pp. 51–56. doi:10.1109/NFV-SDN50289.2020.9289894.
8. [8] M. Abdallah, N. An Le Khac, H. Jahromi, A. Delia Jurcut, A Hybrid CNN-LSTM Based Approach for Anomaly Detection Systems in SDNs, in: 16th Int. Conf. Availability, Reliab. Secur., ACM, New York, NY, USA, 2021: pp. 1–7. doi:10.1145/3465481.3469190.

9. [9] H. Polat, O. Polat, A. Cetin, Detecting DDoS Attacks in Software-Defined Networks Through Feature Selection Methods and Machine Learning Models, Sustainability. 12 (2020) 1035. doi:10.3390/su12031035.
10. [10] M. Revathi, V. V. Ramalingam, B. Amutha, A Machine Learning Based Detection and Mitigation of the DDOS Attack by Using SDN Controller Framework, Wirel. Pers. Commun. (2021). doi:10.1007/s11277-021-09071-1.
11. [11] S. Chakraborty, SDN Intrusion Detection, 2021. (2021). https://www.kaggle.com/subhajournal/sdn-intrusion-detection (accessed November 16, 2021).
12. [12] F.A. Hashim, K. Hussain, E.H. Houssein, M.S. Mabrouk, W. Al-Atabany, Archimedes optimization algorithm: a new metaheuristic algorithm for solving optimization problems, Appl. Intell. 51 (2021) 1531–1551. doi:10.1007/s10489-020-01893-z.
13. [13] E.H. Houssein, B.E. Helmy, H. Rezk, A.M. Nassef, An enhanced Archimedes optimization algorithm based on Local escaping operator and Orthogonal learning for PEM fuel cell parameter identification, Eng. Appl. Artif. Intell. 103 (2021) 104309. doi:https://doi.org/10.1016/j.engappai.2021.104309.
14. [14] N. Van Thieu, Archimedes optimization algorithm code, 2021. (2021). https://github.com/thieu1995/mealpy/blob/master/mealpy/math_based/AOA.py (accessed November 19, 2021).
15. [15] H. Wang, W. Li, DDosTC: A Transformer-Based Network Attack Detection Hybrid Mechanism in SDN, Sensors. 21 (2021) 5047. doi:10.3390/s21155047.
16. [16] V. Tümen, B. Ergen, Intersections and crosswalk detection using deep learning and image processing techniques, Phys. A Stat. Mech. Its Appl. 543 (2020) 123510. doi:10.1016/j.physa.2019.123510.
17. [17] E. Başaran, Z. Cömert, A. Şengür, Ü. Budak, Y. Çelik, M. Toğaçar, Chronic Tympanic Membrane Diagnosis based on Deep Convolutional Neural Network, in: 2019 4th Int. Conf. Comput. Sci. Eng., 2019: pp. 1–4. doi:10.1109/ubmk.2019.8907070.
18. [18] M. Liu, F. Li, H. Yan, K. Wang, Y. Ma, L. Shen, M. Xu, A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer’s disease, Neuroimage. 208 (2020) 116459. doi:https://doi.org/10.1016/j.neuroimage.2019.116459.
19. [19] A. Ahmed, K. Shaalan, S. Toral, Y. Hifny, A Multimodal Approach to Improve Performance Evaluation of Call Center Agent, Sensors (Basel). 21 (2021) 2720. doi:10.3390/s21082720.
20. [20] N. Tötsch, D. Hoffmann, Classifier uncertainty: evidence, potential impact, and probabilistic treatment, PeerJ Comput. Sci. 7 (2021) e398. doi:10.7717/peerj-cs.398.
21. [21] A. Arı, Ö.F. Alçin, D. Hanbay, Brain MR Image Classification Based on Deep Features by Using Extreme Learning Machines, Biomed. J. Sci. Tech. Res. 25 (2020). doi:10.26717/bjstr.2020.25.004201.
22. [22] Y. Bai, E. Yang, B. Han, Y. Yang, J. Li, Y. Mao, G. Niu, T. Liu, Understanding and Improving Early Stopping for Learning with Noisy Labels, (2021). http://arxiv.org/abs/2106.15853.
23. [23] M.K. Bohmrah, H. Kaur, Classification of Covid-19 patients using efficient fine-tuned deep learning DenseNet model, Glob. Transitions Proc. 2 (2021) 476–483. doi:10.1016/j.gltp.2021.08.003.