Saldırı tespiti için metasezgisel tabanlı özellik seçim yöntemi kullanan evrişimli sinir ağı modelleri

Öz

Bu çalışma, Evrişimsel sinir ağları (CNN'ler) ile birleştirilmiş bir meta-sezgisel tabanlı özellik seçim yöntemi kullanarak izinsiz giriş tespiti için yeni bir yaklaşım önermektedir. Önerilen seçme yöntemi, farklı veri kümelerinden en önemli özellikleri seçmek için bir karar ağacı ve metasezgisel bir algoritma kullanır. Seçilen özellikler daha sonra izinsiz giriş tespitinin doğruluğunu artırmak için sırasıyla ResNet50, VGG16 ve EfficientNet modelleri için veri girişi sağlarlar. Veri setindeki deneysel sonuçlar, önerilen yöntemin farklı kriterler açısından referans olabileceğini göstermektedir. Ön eğitim aşamasında özellik seçimi yapıldığından, önerilen yöntemin çevrimiçi ve gerçek zamanlı saldırı tespiti için uygun olduğu belirlenmiştir. Bu çalışmanın bulguları, önerilen yöntemin ağ trafiğindeki izinsiz girişleri etkili bir şekilde tanımlama ve sınıflandırma potansiyeli olduğunu göstermektedir

Anahtar Kelimeler

• İzinsiz giriş tespiti
• Konvolüsyonel Sinir Ağı
• Meta-sezgisel algoritmalar
• Özellik seçimi
• Karar Ağacı.

Convolutional neural network models using metaheuristic based feature selection method for intrusion detection

Öz

This paper proposes a novel approach for intrusion detection using a metaheuristic-based feature selection method combined with convolutional neural networks (CNNs). The feature selection method employs a decision tree and a metaheuristic algorithm to select the most important features from different datasets. The selected features are then feed into CNNs, including ResNet50, VGG16, and EfficientNet, to improve the accuracy of intrusion detection. Experimental results on several benchmark datasets show that the proposed method can be promising in terms of different criteria. The proposed method is suitable for online and real-time intrusion detection as feature selection is performed during the pre-training phase. The findings of this study demonstrate the potential of the proposed method to effectively identify and classify intrusions in network traffic.

Anahtar Kelimeler

• Intrusion detection
• Convolutional Neural Network
• Meta-heuristic algorithms
• Feature selection
• Decision Tree

Kaynakça

1. 1. Liao H.-J., C.-H. Lin R., Lin Y.-C., and Tung K.-Y., ntrusion detection system: A comprehensive review, Journal of Network and Computer Applications, 36 (1), 16–24, 2013.
2. 2. Gümüşbaş D., Yıldırım T., Genovese A., and Scotti F., A comprehensive survey of databases and deep learning methods for cybersecurity and intrusion detection systems, IEEE Systems Journal, 15 (2), 1717–1731, 2020.
3. 3. Agrawal P., Abutarboush H. F., Ganesh T., and A. Mohamed W., Metaheuristic algorithms on feature selection: A survey of one decade of research, Ieee Access, 9, 26766–26791, 2021.
4. 4. Kim J., Kim H., Shim M., and Choi E., CNN-based network intrusion detection against denial-of-service attacks, Electronics, 9 (6), 916, 2020.
5. 5. Dandıl E., Yıldırım M.S., Selvi A.O., Uzun S., Automated liver segmentation using Mask R-CNN on computed tomography scans, Journal of the Faculty of Engineering and Architecture of Gazi University, 37 (1), 29-46, 2022.
6. 6. Aymaz S., A new hybrid approach for multi-focus image fusion using CNN and SVM methods, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (2), 1123-1136, 2024.
7. 7. Saidi R., Bouaguel W., and Essoussi N., Hybrid feature selection method based on the genetic algorithm and pearson correlation coefficient, Machine learning paradigms: theory and application, 3–24, 2019.
8. 8. Alzaqebah M. et al., Hybrid feature selection method based on particle swarm optimization and adaptive local search method, International Journal of Electrical and Computer Engineering, 113, 2414, 2021.

9. 9. Hasan H. and Tahir N. M., Feature selection of breast cancer based on principal component analysis, 6th International Colloquium on Signal Processing & its Applications, 1–4, 2010.
10. 10. Fang L. et al., Feature selection method based on mutual information and class separability for dimension reduction in multidimensional time series for clinical data, Biomedical Signal Processing and Control, 21, 82–89, 2015.
11. 11. Dincalp U., Güzel M. S., Sevine O., Bostanci E., and Askerzade I., Anomaly based distributed denial of service attack detection and prevention with machine learning, 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 1–4, 2018.
12. 12. Vijayanand R., Devaraj D., and Kannapiran B., Intrusion detection system for wireless mesh network using multiple support vector machine classifiers with genetic-algorithm-based feature selection, Computers & Security, 77, 304–314, 2018.
13. 13. Bakour K., G. S. Daş, and Ünver H. M., ‘An intrusion detection system based on a hybrid Tabu-genetic algorithm’,International Conference on Computer Science and Engineering (UBMK), 215–220, 2017.
14. 14. Uysal E. İ., Demircioğlu G., Kale G., Bostanci E., Güzel M. S., and Mohammed S. N., ‘Network Anomaly Detection System using Genetic Algorithm, Feature Selection and Classification’, 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 1–5, 2019.
15. 15. Jasim A. D. and others, A survey of intrusion detection using deep learning in internet of things, Iraqi Journal for Computer Science and Mathematics, 3 (1), 83–93, 2022.
16. 16. Ahmad Z., Shahid Khan A., Wai Shiang C., Abdullah J., and Ahmad F., Network intrusion detection system: A systematic study of machine learning and deep learning approaches, Transactions on Emerging Telecommunications Technologies, 32 (1), 4150, 2021.
17. 17. Rafique M. Ali F., M., Qureshi A. S., Khan A., and Mirza A. M., Malware classification using deep learning based feature extraction and wrapper based feature selection technique, arXiv preprint arXiv:1910. 10958, 2019.
18. 18. Devi E. M. and Devi R. C. x, Feature selection in intrusion detection grey wolf optimizer, Asian Journal of Research in Social Sciences and Humanities, 7 (3), 671–682, 2017.
19. 19. Wang Z. Li, W., Yan Y., and Li Z., ‘PS--ABC: A hybrid algorithm based on particle swarm and artificial bee colony for high-dimensional optimization problems’, Expert Systems with Applications, 42, 22, 8881–8895, 2015.
20. 20. Protić D. D., ‘Review of KDD Cup ‘99, NSL-KDD and Kyoto 2006+ datasets’, Vojnotehnički glasnik/Military Technical Courier, 66 (3), 580–596, 2018.
21. 21. Sharafaldin I., Lashkari A.H., Ghorbani A. A., Toward generating a new intrusion detection dataset and intrusion traffic characterization, ICISSp. 1, 108–116, 2018.
22. 22. Sharafaldin I., Gharib A., Lashkari A.H., Ghorbani A. A., Towards a reliable intrusion detection benchmark dataset, Software Networking, 1, 177–200, 2018.
23. 23. Simonyan K. and Zisserman A., Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv: 1409. 1556, 2014.
24. 24. He K., Zhang X., Ren S., and Sun J., Deep residual learning for image recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778, 2016.
25. 25. Tan M. and Le Q., Efficientnet: Rethinking model scaling for convolutional neural networks, in International conference on machine learning, 6105–6114, 2019.
26. 26. Li Z., Qin Z., Huang K., Yang X., and Ye S., Intrusion detection using convolutional neural networks for representation learning, in Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, 14-18, Proceedings, Part V, 858–866, 2017.
27. 27. Zhipeng Li,.et al., Intrusion detection using convolutional neural networks for representation learning, Neural Information Processing: 24th International Conference, ICONIP, Guangzhou, China, November 14–18, 2017.
28. 28. Hu J., Liu C., and Cui Y., An improved CNN approach for network intrusion detection system, Int. J. Netw. Secur, 23 (4), 569–575, 2021.
29. 29. Tang T. et al., Deep Learning Approach for Network Intrusion Detection in Software Defined Networking, The International Conference on Wireless Networks and Mobile Communications IEEE . ISBN 978-1-5090-3837-4, 2016.
30. 30. Chowdhury M., Frederick H., Glenn K., Jiang L., Chunsheng X., and Hongyi W., A Few-shot Deep Learning Approach for Improved Intrusion Detection, IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON). New York, NY, USA: IEEE: 456-462, 2017.