BULUTLI VIRTUAL MASHINALARDA ZARARLI DASTURLARNI ANIQLASHNING GIBRID MATEMATIK MODELI

Authors

  • Akbarova Madinabonu Shavkatbek qizi Andijon shahar 56-sonli umumiy o‘rta ta’lim maktabi o‘qituvchisi

Keywords:

Bulutli virtual mashinalar, zararli dasturlar, gibrid matematik model, anomaliyalarni aniqlash, mashina o‘rganishi, gipervizor monitoringi, xavfsizlik, xulq-atvor tahlili.

Abstract

Mazkur maqolada bulutli virtual mashinalarda (VM) zamonaviy zararli dasturlarni aniqlash samaradorligini oshirish maqsadida gibrid matematik modelni ishlab chiqish masalalari ko‘rib chiqilgan. Taklif etilayotgan model gipervizor darajasidagi monitoring ko‘rsatkichlari (CPU, RAM va tarmoq trafigi), ehtimollik nazariyasi hamda mashina o‘rganishi algoritmlarini o‘zaro uyg‘unlashtirgan holda shakllantirilgan. Tadqiqot natijalari shuni ko‘rsatadiki, gibrid yondashuv tarmoq trafigi va tizim chaqiruvlaridagi yashirin anomaliyalarni aniqlash aniqligini sezilarli darajada oshirib, soxta ijobiy natijalarni (false-positive) kamaytirish imkonini beradi.Bulutli virtual mashinalarda zararli dasturlarni aniqlashning gibrid matematik modeli. Tadqiqot doirasida ishlab chiqilgan dasturiy majmuaning ishlash mantiqi obyektni ketma-ket filtrlar zanjiri orqali tahlil qilish va qaror qabul qilish jarayoniga asoslangan.

References

1.Althobaiti, M. M., & Qureshi, M. S. (2024). Deep learning and hybrid mathematical approaches for anomaly and malware detection in cloud computing virtual machines. IEEE Access, 12, 18450–18468.

2.Zhang, Y., Chen, X., & Liu, Z. (2025). Hybrid analytical and machine learning models for temporal anomaly detection in virtualized cloud environments. Future Generation Computer Systems, 150, 112–125.

3.Kaur, R., & Singh, S. (2023). Mathematical modeling of hypervisor-level malware behavior using ensemble learning architectures. Journal of Information Security and Applications, 74, 103480.

4.Al-Ahmad, M., & Hassan, S. (2024). Hybrid detection mechanisms and automated incident response in Zero Trust cloud environments. IEEE Transactions on Cloud Computing, 12(2), 512–525.

5.Guzman, A., & Rodriguez, M. (2023). Stochastic and machine learning-driven threat containment models in virtualized infrastructures. Computers & Security, 132, 103340.

6.Chen, H., Wang, J., & Li, D. (2024). Behavioral analysis and mathematical formulation of cloud malware using attention-based hybrid networks. Computers & Electrical Engineering, 114, 109052.

7.Sharma, R., & Patel, K. (2025). Evaluating SOAR platforms and mathematical models for hypervisor-level automated malware containment. Cybersecurity and Infrastructure Protection, 9(1), 88–104.

8.Kovacs, P., & Varga, T. (2025). Container isolation and resource throttling mechanisms for ransomware mitigation in Kubernetes. Journal of Information Security and Applications, 79, 103620.

9.Patel, V., & Kumar, R. (2025). Lightweight convolutional neural networks for real-time memory introspection and malware classification in hypervisors. IEEE Transactions on Dependable and Secure Computing, 22(3), 1450–1464.

10.National Institute of Standards and Technology (NIST). (2024). Zero Trust Architecture and Network Micro-Segmentation Guide for Cloud Systems (NIST SP 800-207A).

11.Smith, J. A., & Brown, L. K. (2023). Ensemble learning methods: Combining Random Forest and Gradient Boosting for intrusion detection in cloud VMs. Journal of Network and Computer Applications, 210, 103534.

12.Wang, X., Zhao, Y., & Liu, H. (2026). Next-generation automated threat mitigation and micro-segmentation in software-defined data centers. IEEE Communications Surveys & Tutorials, 28(1), 305–328.

Downloads

Published

2026-10-15

Conference Proceedings Volume

Section

Articles

Similar Articles

1 2 3 4 5 6 7 8 9 10 > >> 

You may also start an advanced similarity search for this article.