Uneingeschränkter Zugang

Research on Intelligent Network Security Event Detection and Emergency Disposal Technology

Wang Xiaoxia

Wang Xiaoxia

Inner Mongolia Police Professional CollegeHohhot, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Xiaoxia, Wang
  
31. März 2025
Research on Intelligent Network Security Event Detection and Emergency Disposal Technology's Cover Image
Über diesen Artikel
Vorheriger Artikel
Nächster Artikel
Zitieren
COVER HERUNTERLADEN
Online veröffentlicht: 31. März 2025
Eingereicht: 11. Nov. 2024
Akzeptiert: 14. Feb. 2025
DOI: https://doi.org/10.2478/amns-2025-0819
Schlüsselwörter
© 2025 Wang Xiaoxia, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

CNN-LSTM_HMNID model structure
CNN-LSTM_HMNID model structure

Figure 2.

CNN structure
CNN structure

Figure 3.

LSTM structure
LSTM structure

Figure 4.

Realization method of intelligent emergency disposal technology
Realization method of intelligent emergency disposal technology

Figure 5.

Loss curve
Loss curve

Figure 6.

Confusion Matrix
Confusion Matrix

Figure 7.

Response time
Response time

Figure 8.

System recovery time after attack
System recovery time after attack

Figure 9.

Change of model performance with time
Change of model performance with time

Identification of different types of attacks in different models

Attack type Model Precision accuracy Recall F1 score
CNN-LSTM_HMNID 0.95 0.96 0.94 0.945
DDoS attack SVM 0.90 0.92 0.88 0.89
Random Forest 0.92 0.93 0.90 0.91
CNN-LSTM_HMNID 0.93 0.95 0.96 0.945
Port scanning SVM 0.88 0.90 0.92 0.90
Random Forest 0.90 0.92 0.91 0.905
CNN-LSTM_HMNID 0.91 0.93 0.92 0.915
phishing SVM 0.85 0.87 0.86 0.855
Random Forest 0.87 0.89 0.88 0.875

Accuracy and false alarm rate of model recognition

data set Network traffic type Recognition accuracy (%) False alarm rate (%)
Normal flow 98.5 1.5
Data set 1 Abnormal traffic (DDoS attack) 96.2 3.8
Abnormal traffic (port scanning) 97.8 2.2
Normal flow 97.7 2.3
Data set 2 Abnormal traffic (phishing) 95.5 4.5
Abnormal traffic (malware download) 98.2 1.8
Comprehensive data set All traffic types 97.3 2.7

Performance evaluation index

Performance index Normal flow Abnormal flow
Precision 0.97 0.95
Recall 0.98 0.96
F1 Score 0.975 0.955
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
1 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Biologie, Biologie, andere, Mathematik, Angewandte Mathematik, Mathematik, Allgemeines, Physik, Physik, andere
Zeitschrift RSS Feed