Skip to main navigation menu Skip to main content Skip to site footer

Vol. 12 No. 11 (2025)
International Multidisciplinary Journal for Research & Development

Articles

ARTIFICIAL INTELLIGENCE IN THE NETWORK: AUTOMATIC TRAFFIC ANALYSIS AND THREAT FORECASTING

Published 2025-11-25

  • M.Z. Tursunalieva

M.Z. Tursunalieva
Student of Applied Mathematics, Fergana State University

Abstract

This article highlights the increasing complexity of manual control of flows in network infrastructure due to their increasing volume, especially the difficulties in identifying slowly developing hidden threats. The ability to analyze traffic in real time, identify anomalies, and detect threats early is due to the ability of artificial intelligence algorithms to detect subtle changes. By forming characteristics, organizing data, and applying a corresponding model, the system will be able to identify even the smallest differences between packets. In practical cases, gradual changes in port switching, detection of slow flows directed to unknown servers, or hidden behavior characteristic of bots have shown the advantages of artificial intelligence. Such an approach will allow strengthening security, reducing the burden on administrators, and detecting suspicious activity at an early stage, demonstrating high efficiency in identifying threats, which in appearance are practically indistinguishable from regular traffic.

Keywords

network traffic, anomaly detection, artificial intelligence, forecasting, information security

PDF

References

  1. Zhang J., Lee W. Machine Learning in Network Security: Anomaly Detection Techniques // IEEE Transactions on Network and Service Management. - 2022.
  2. Buczak A. L., Guven E. A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection // IEEE Communications Surveys & Tutorials. - 2019.
  3. Tursunaliyeva M.Z. Optimization of network traffic with the help of artificial intelligence based on edge computing: a new methodological approach // Science and Innovation. International Scientific Journal. - 2021. - Vol. 4, No. 9. - P. 76-79. - doi:10.5281/zenodo.17258224.
  4. Tursunaliyeva M. Energy efficiency in neural networks: problems of optimizing large models // Science and Innovation. International Scientific Journal. - 2021. - Vol. 4, No. 11. - P. 59-61. - DOI: 10.5281/zenodo.17674536.
  5. Cisco Systems. AI-Driven Network Security Whitepaper. - 2023.
  6. Python Software Foundation. Python Documentation. - Access mode: https://docs.python.org
  7. Wireshark Team. Wireshark User Guide. - Access mode: https://www.wireshark.org/docs/

Downloads

Download data is not yet available.