Network traffic analysis based on deep learning algorithms
Bibliographic entry
Xia, E. Network traffic analysis based on deep learning algorithms / E. Xia, L. Fan // Новые горизонты – 2025 : сборник материалов XII Белорусско-китайского молодежного инновационного форума, 27–28 ноября 2025 года / Белорусский национальный технический университет. – Минск : БНТУ, 2025. – Т. 1. – С. 106-107.
Abstract
This paper introduces a novel hierarchical model integrating 2D-CNN and Bi-LSTM-Attention for improved network traffic analysis. We standardized the USTC-TFC-2016 and CICDDoS 2019 datasets into 40 × 40 grayscale images, extracting spatial features with 2D-CNN and temporal dependencies with Bi-LSTMAttention. Our model demonstrated superior accuracy and robustness over conventional approaches, with capabilities for real-time malicious traffic detection.