Skip to main navigation Skip to search Skip to main content

AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization

  • Akshat Gaurav
  • , Brij B. Gupta
  • , Priyanka Chaurasia
  • , Varsha Arya
  • , Razaz Waheeb Attar
  • , Kwok Tai Chui

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Ensuring secure and efficient intrusion detection in Software-Defined Networking (SDN) within network virtualization is crucial for modern cybersecurity. In this context, this work presents an AI-powered hybrid deep learning model integrating CNN, LSTM, GRU, and a Transformer Encoder for feature selection. SMOTE is used to balance class distributions, therefore strengthening the model. With ROC-AUC values of 0.9628, and accuracy of 82%, therefore attesting to improved classification performance. For virtualized SDN settings, this method presents an adaptive intrusion detection, hence improving network security and dependability for useful cyber-defense purposes.

Original languageEnglish
Title of host publication2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025
ISBN (Electronic)9798331529918
DOIs
Publication statusPublished - 2025
Event26th IEEE International Conference on High Performance Switching and Routing, HPSR 2025 - Osaka, Japan
Duration: 20 May 202522 May 2025

Publication series

NameIEEE International Conference on High Performance Switching and Routing, HPSR
ISSN (Print)2325-5595
ISSN (Electronic)2325-5609

Conference

Conference26th IEEE International Conference on High Performance Switching and Routing, HPSR 2025
Country/TerritoryJapan
CityOsaka
Period20/05/2522/05/25

Keywords

  • Deep Learning
  • Forensic-Based Feature Selection
  • Intrusion Detection System (IDS)
  • Network Virtualization
  • Software-Defined Networking (SDN)

Fingerprint

Dive into the research topics of 'AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization'. Together they form a unique fingerprint.

Cite this