A Scalable Framework for Real-Time Network Security Traffic Analysis and Attack Detection Using Machine and Deep Learning

• DOI: 10.3390/platforms3020007
• Publication Date: 2025-04-11T07:45:23Z
• Authors: Zineb Maasaoui; Mheni Merzouki; Abdella Battou; Ahmed Lbath
• Keywords: Traffic Analysis

This paper presents an advanced framework for real-time monitoring and analysis of network traffic endpoint security in large-scale enterprises by addressing the increasing complexity frequency cyber-attacks. Our Network Security Traffic Analysis Platform employs a comprehensive technology stack including Elastic Stack, ZEEK, Osquery, Kafka, GeoLocation data. By integrating supervised machine learning models trained on UNSW-NB15 dataset, we evaluate Random Forest (RF), Decision Trees (DT), Support Vector Machines (SVM), with classifier achieving notable accuracy 99.32%. Leveraging Artificial Intelligence Natural Language Processing, apply BERT model Byte-level Byte-pair tokenizer to enhance network-based attack detection IoT systems. Experiments UNSW-NB15, TON-IoT, Edge-IIoT datasets demonstrate our platform’s superiority over traditional methods multi-class classification tasks, near-perfect dataset. Furthermore, Platform’s ability produce actionable insights through charts, tables, histograms, other visualizations underscores its capability static dual approach provides robust foundation developing scalable, efficient, automated solutions, essential managing evolving threats modern networks.