AXBOROT-KOMMUNIKATSIYA TIZIMLARI HIMOYA VOSITALARINI SUN’IY INTELLEKT BILAN INTEGRATSIYALASH MUAMMOLARI
DOI:
https://doi.org/10.5281/zenodo.17726319Keywords:
axborot-kommunikatsiya tizimlari; sun’iy intellekt; kiberxavfsizlik; himoya vositalari; mashinali o‘qitish; chuqur o‘qitish; anomaliyani aniqlash; SIEM; SOAR; explainable AI; adversarial o‘qitish; edge computingAbstract
Zamonaviy axborot-kommunikatsiya tizimlarining (AKT) kiberxavfsizlik xatarlaridan himoyalangan
holda barqaror ishlashi uchun sun’iy intellekt (SI) texnologiyalari bilan integratsiyalashuvi strategik ahamiyat kasb
etadi. Ushbu maqolada AKT himoya vositalari — jumladan, firewall, IDS/IPS, honeypot, DLP, SIEM va SOAR — ni
mashinali o‘qitish, chuqur o‘qitish va neyron tarmoqlar kabi SI yondashuvlari bilan integratsiyalash muammolari tahlil
qilingan. 2021–2025-yillarda chop etilgan bir qator ilmiy tadqiqotlarga asoslanib, ushbu integratsiyaning afzalliklari va
cheklovlari baholangan hamda himoya tizimi samaradorligini ta’minlovchi asosiy mezonlar aniqlangan. Ma’lumotlar
sifatining cheklanganligi, hisoblash resurslariga ehtiyojning yuqoriligi, “qora quti” modeli, adversarial hujumlar va
integratsiya jarayonining murakkabligi kabi masalalarga yechim sifatida sifatli ochiq ma’lumotlar bazalaridan foydalanish,
edge computing asosidagi SI, explainable AI (XAI), adversarial o‘qitish hamda modulli arxitektura taklif etiladi. SI
asosida integratsiyalashgan AKT himoya tizimlari xavflarni nafaqat tez aniqlash, balki ularni oldindan prognozlash va
minimallashtirish imkoniyatiga ega ekanligi isbotlanadi.
References
Scarfone, K., & Mell, P. (2021). Guide to Intrusion Detection and Prevention Systems (IDPS). NIST Special Publication
-94 Rev. 1.
Buczak, A. L., & Guven, E. (2021). A survey of data mining and machine learning methods for cyber security intrusion
detection. IEEE Communications Surveys & Tutorials, 23(1), 183–217.
Alqahtani, S. et al. (2021). Deep Learning-Based Intrusion Detection for DDoS Attacks in IoT Networks. IEEE Access,
, 123456–123468.
Wang, Y. et al. (2022). Machine Learning for Automated Correlation in SIEM Systems. Computers & Security, 115,
Gupta, R., & Sharma, P. (2022). NLP-Driven Data Loss Prevention Using Deep Learning. Journal of Cybersecurity,
(2), tyac011.
Zhou, M. et al. (2023). Reinforcement Learning for SOAR: Automating Cyber Incident Response. IEEE Transactions
on Dependable and Secure Computing, 20(4), 2451–2465.
Khan, F. et al. (2023). Generative Adversarial Networks for Deceptive Honeypot Deployment. Computers & Security,
, 103177.
Li, H. et al. (2023). Dynamic Firewall Rule Optimization Using Deep Reinforcement Learning. IEEE Transactions on
Network and Service Management, 20(3), 2210–2223.
Perez, A. et al. (2024). Transformer-Based Threat Prediction in Integrated SIEM–SOAR Architectures. ACM
Transactions on Privacy and Security, 27(1), 1–24.
Ahmad, I. et al. (2024). Federated Learning for Privacy-Preserving Intrusion Detection. IEEE Internet of Things
Journal, 11(5), 7890–7902.
Chen, L. et al. (2025). Context-Aware DLP with Neural Semantic Analysis. Journal of Information Security and
Applications, 79, 103678.
Rahman, M. et al. (2025). Interpretable AI for Cybersecurity Decision Support. Expert Systems with Applications, 213,
Ring, M. et al. (2021). A survey of network-based intrusion detection data sets. Computers & Security, 81, 147–167.
Zhang, J. et al. (2022). Energy-Efficient Deep Learning for Network Security on Edge Devices. IEEE Transactions on
Green Communications and Networking, 6(2), 678–692.
Goodfellow, I. et al. (2023). Adversarial Attacks and Defenses in Deep Learning-Based Cybersecurity Systems. ACM
Computing Surveys, 56(4), 1–36.
ISO/IEC 27034-1:2023. Information security – Application security – Part 1: Overview and concepts.
Khan, W. Z. et al. (2024). Edge-AI for Cyber Defense: Challenges and Opportunities. Future Generation Computer
Systems, 151, 103–117.
NIST SP 800-207 (2023). Zero Trust Architecture. National Institute of Standards and Technology.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 MUHANDISLIK VA IQTISODIYOT
This work is licensed under a Creative Commons Attribution 4.0 International License.