Information and communication and chemical technologies

Vol. 1 No. 30 (2026) / 2026-03-30 / Number of views: 276

NETWORK TRAFFIC ANALYSIS FOR DETECTING THE DISTRIBUTION OF FALSE CONTENT OVER THE NETWORK

Authors

L.N. Gumilyov Eurasian National University
https://orcid.org/0009-0004-0446-2402
L.N. Gumilyov Eurasian National University
https://orcid.org/0000-0001-5730-4644
L.N. Gumilyov Eurasian National University
https://orcid.org/0000-0002-9162-6791

Keywords

false content, deepfakes, information security, network traffic analysis, neural networks, Scapy, MesoNet, automated analysis, disinformation, digital forensics

Link to DOI:

https://doi.org/10.58805/kazutb.v.1.30-1213

How to quote

Sarsembayeva Z.А., et al. “NETWORK TRAFFIC ANALYSIS FOR DETECTING THE DISTRIBUTION OF FALSE CONTENT OVER THE NETWORK”. Vestnik KazUTB, vol. 1, no. 30, Mar. 2026, doi:10.58805/kazutb.v.1.30-1213.

Abstract

The rapid development of digital technologies and artificial intelligence has opened up new opportunities for the dissemination of false information. In recent years, deepfake content, which is not authentic but visually convincing, has become widespread. Current studies on detecting false content are mostly limited to visual-level analysis, while effective methods for identifying it at the network level remain insufficiently explored. Therefore, the main objective of this research is to propose effective technical approaches for detecting false content, including deepfakes, through network traffic analysis. This study applied HTTP traffic analysis, automatic file extraction, and deepfake detection using the MesoNet neural network model. The research utilized Scapy, PyTorch, and Docker technologies. The results demonstrated that the proposed method can accurately detect deepfake content at the network traffic level in real time. The system automatically identifies malicious content and promptly sends alerts via Telegram, which has significant practical value for ensuring information security.