MindFlow: A Network Traffic Anomaly Detection Model Based on MindSpore

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xiang, Qiuyan, Wu, Shuang, Wu, Dongze, Liu, Yuxin, Qin, Zhenkai
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912344970362880
author Xiang, Qiuyan
Wu, Shuang
Wu, Dongze
Liu, Yuxin
Qin, Zhenkai
author_facet Xiang, Qiuyan
Wu, Shuang
Wu, Dongze
Liu, Yuxin
Qin, Zhenkai
contents With the wide application of IoT and industrial IoT technologies, the network structure is becoming more and more complex, and the traffic scale is growing rapidly, which makes the traditional security protection mechanism face serious challenges in dealing with high-frequency, diversified, and stealthy cyber-attacks. To address this problem, this study proposes MindFlow, a multi-dimensional dynamic traffic prediction and anomaly detection system combining convolutional neural network (CNN) and bi-directional long and short-term memory network (BiLSTM) architectures based on the MindSpore framework, and conducts systematic experiments on the NF-BoT-IoT dataset. The experimental results show that the proposed model achieves 99% in key metrics such as accuracy, precision, recall and F1 score, effectively verifying its accuracy and robustness in network intrusion detection.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17678
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MindFlow: A Network Traffic Anomaly Detection Model Based on MindSpore
Xiang, Qiuyan
Wu, Shuang
Wu, Dongze
Liu, Yuxin
Qin, Zhenkai
Computers and Society
With the wide application of IoT and industrial IoT technologies, the network structure is becoming more and more complex, and the traffic scale is growing rapidly, which makes the traditional security protection mechanism face serious challenges in dealing with high-frequency, diversified, and stealthy cyber-attacks. To address this problem, this study proposes MindFlow, a multi-dimensional dynamic traffic prediction and anomaly detection system combining convolutional neural network (CNN) and bi-directional long and short-term memory network (BiLSTM) architectures based on the MindSpore framework, and conducts systematic experiments on the NF-BoT-IoT dataset. The experimental results show that the proposed model achieves 99% in key metrics such as accuracy, precision, recall and F1 score, effectively verifying its accuracy and robustness in network intrusion detection.
title MindFlow: A Network Traffic Anomaly Detection Model Based on MindSpore
topic Computers and Society
url https://arxiv.org/abs/2504.17678