| DC Field | Value | Language |
|---|
| dc.contributor.author | Xia Enduo | - |
| dc.contributor.author | Fan Linda | - |
| dc.contributor.author | He Hongyan | - |
| dc.coverage.spatial | Минск | en_US |
| dc.date.accessioned | 2025-12-02T08:39:02Z | - |
| dc.date.available | 2025-12-02T08:39:02Z | - |
| dc.date.issued | 2025 | - |
| dc.identifier.citation | Xia Enduo. Network traffic analysis based on deep learning algorithms / Xia Enduo, Fan Linda, He Hongyan // Информационные технологии и системы 2025 (ИТС 2025) : материалы международной научной конференции, Минск, 19 ноября 2025 / Белорусский государственный университет информатики и радиоэлектроники ; редкол.: Л. Ю. Шилин [и др.]. – Минск, 2025. – С. 137–138. | en_US |
| dc.identifier.uri | https://libeldoc.bsuir.by/handle/123456789/62254 | - |
| dc.description.abstract | We propose a unified anomaly detection framework based on CNN-BiLSTM-Attention to address the low accuracy
and high false positive rates of existing traffic-based network anomaly detection methods. The framework represents
each network session as a 2D grayscale image, uses 2D-CNN for spatial feature extraction, BiLSTM for long-range
temporal dependency capture, and an attention mechanism to highlight the most discriminative features. Experiments
on the USTC-TFC-2016 and CICDDoS 2019 datasets show that this framework significantly outperforms state-of the-art methods in accuracy, detection rate, and false positive rate, demonstrating its effectiveness and generalization
for network traffic classification. | en_US |
| dc.language.iso | ru | en_US |
| dc.publisher | БГУИР | en_US |
| dc.subject | материалы конференций | en_US |
| dc.subject | network anomaly | en_US |
| dc.subject | state-of the-art methods | en_US |
| dc.title | Network traffic analysis based on deep learning algorithms | en_US |
| dc.type | Article | en_US |
| Appears in Collections: | ИТС 2025
|
