KATTA HAJMDAGI TARMOQ TRAFIKLARINI INTELLEKTUAL TAHLIL QILISH UCHUN GIBRID DEEP LEARNING MODELINI ISHLAB CHIQISH

Jurayev O‘tkirbek Murodullo o‘g‘li

Authors

Jurayev O‘tkirbek Murodullo o‘g‘li Iqtisodiyot va pedagogika universiteti

Keywords:

tarmoq trafiki, IDS/NIDS, gibrid deep learning, CNN, BiLSTM, transformer, imbalanced data, real vaqt tahlili

Abstract

Katta hajmdagi tarmoq trafiklari (enterprise, bulut, IoT, SDN) real vaqt rejimida tez qayta ishlanishi, turli hujum turlarini aniq ajratishi va klasslar nomutanosibligi (imbalanced data) sharoitida barqaror ishlashi zarur [14]. CICIDS2017 va UNSW-NB15 kabi ommaviy benchmark ma’lumotlar to‘plamlari asosida baholash metodikasi beriladi, nomutanosiblikni kamaytirish uchun SMOTE/Borderline - SMOTE, focal loss, class weights va threshold tuning kabi yechimlar taklif qilinadi [6]. Natijada yuqori aniqlik bilan bir qatorda, real vaqt ishlashi uchun hisoblash samaradorligi (latency/throughput) ham mezon sifatida qo‘yiladi.

References

1. Canadian Institute for Cybersecurity. (2017). CICIDS2017 Dataset (IDS 2017). University of New Brunswick.

2. UNSW Canberra Cyber. (2015). The UNSW-NB15 Dataset. University of New South Wales.

3. Ullah, F., Mahmoud, Q. H., & Jabbar, S. (2024). IDS-INT: Intrusion detection system using transformer-based transfer learning for imbalanced network traffic. Computers & Security, 136, 103456.

4. Long, Z., Chen, Y., & Li, H. (2024). A transformer-based network intrusion detection approach in a cloud environment. Cluster Computing, 27(2), 1453–1468.

5. Xi, C., Wang, J., & Zhao, L. (2024). IDS-MTran: A novel multi-scale transformer-based network intrusion detection model. Scientific Reports, 14, 74214.

6. Zhang, C., Liu, Y., & Huang, X. (2025). Hybrid CNN-BiLSTM-Transformer model with Borderline-SMOTE for imbalanced network intrusion detection. Sensors, 25(9), 2725.

8. Engelen, G., & Doyen, G. (2021). Troubleshooting an intrusion detection dataset: Representativeness challenges in CICIDS2017. Proceedings of the WTMC Workshop, 45–52.

9. Ataa, M. S., Abdelsalam, M., & Youssef, A. (2024). Intrusion detection in software defined networks using deep learning. Scientific Reports, 14, 79001.

10. Kim, G., Lee, S., & Kim, S. (2016). A novel hybrid intrusion detection method integrating anomaly detection with misuse detection. Expert Systems with Applications, 41(4), 1690–1700.

11. Yin, C., Zhu, Y., Fei, J., & He, X. (2017). A

deep learning approach for intrusion detection using recurrent neural networks. IEEE Access, 5, 21954–21961.

12. Shone, N., Ngoc, T. N., Phai, V. D., & Shi, Q. (2018). A deep learning approach to network intrusion detection. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(1), 41–50.

13. Lin, W., Wu, Z., Lin, L., Wen, A., & Li, J. (2020). An intrusion detection model based on combined CNN and LSTM networks. IEEE Access, 8, 165207–165219.

14. Doshi, R., Apthorpe, N., & Feamster, N. (2018). Machine learning DDoS detection for consumer Internet of Things devices. IEEE Security and Privacy Workshops, 29–35.

15. Aljawarneh, S., Aldwairi, M., & Yassein, M. B. (2018). Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model. Journal of Computational Science, 25, 152- 160.