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

doi:10.1109/hpsr64165.2025.11038896

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 proceeding › Conference contribution › peer-review

69 Downloads (Pure)

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 language	English
Title of host publication	2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	9798331529918
ISBN (Print)	9798331529918, 979-8-3315-2992-5
DOIs	https://doi.org/10.1109/hpsr64165.2025.11038896
Publication status	Published online - 19 Jun 2025
Event	2025 IEEE 26th International Conference on High Performance Switching and Routing (HPSR) - Suita, Osaka, Japan Duration: 20 May 2025 → 22 May 2025

Publication series

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

Conference

Conference	2025 IEEE 26th International Conference on High Performance Switching and Routing (HPSR)
Country/Territory	Japan
City	Suita, Osaka
Period	20/05/25 → 22/05/25

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Funding

This research work is supported by National Science and Technology Council (NSTC), Taiwan Grant No. NSTC112-2221-E-468-008-MY3.

Funder number
NSTC112-2221-E-468-008-MY3

Keywords

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

Access to Document

10.1109/hpsr64165.2025.11038896

Paper_priyankaAuthor Accepted Manuscript, 246 KB

Cite this

Gaurav, A., Gupta, B. B., Chaurasia, P., Arya, V., Attar, R. W., & Chui, K. T. (2025). AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization. In 2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025 (pp. 1-6). (IEEE International Conference on High Performance Switching and Routing, HPSR). IEEE. Advance online publication. https://doi.org/10.1109/hpsr64165.2025.11038896

@inproceedings{79ee5edc02194f5198564f3aded3c532,

title = "AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization",

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.",

keywords = "Forensic-Based Feature Selection, Software-Defined Networking (SDN), Intrusion Detection System (IDS), Deep Learning, Network Virtualization",

author = "Akshat Gaurav and Gupta, \{Brij B.\} and Priyanka Chaurasia and Varsha Arya and Attar, \{Razaz Waheeb\} and Chui, \{Kwok Tai\}",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE 26th International Conference on High Performance Switching and Routing (HPSR) ; Conference date: 20-05-2025 Through 22-05-2025",

year = "2025",

month = jun,

day = "19",

doi = "10.1109/hpsr64165.2025.11038896",

language = "English",

isbn = "9798331529918",

series = "IEEE International Conference on High Performance Switching and Routing, HPSR",

publisher = "IEEE",

pages = "1--6",

booktitle = "2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025",

address = "United States",

}

Gaurav, A, Gupta, BB, Chaurasia, P, Arya, V, Attar, RW & Chui, KT 2025, AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization. in 2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025. IEEE International Conference on High Performance Switching and Routing, HPSR, IEEE, pp. 1-6, 2025 IEEE 26th International Conference on High Performance Switching and Routing (HPSR), Suita, Osaka, Japan, 20/05/25. https://doi.org/10.1109/hpsr64165.2025.11038896

AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization. / Gaurav, Akshat; Gupta, Brij B.; Chaurasia, Priyanka et al.
2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025. IEEE, 2025. p. 1-6 (IEEE International Conference on High Performance Switching and Routing, HPSR).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization

AU - Gaurav, Akshat

AU - Gupta, Brij B.

AU - Chaurasia, Priyanka

AU - Arya, Varsha

AU - Attar, Razaz Waheeb

AU - Chui, Kwok Tai

PY - 2025/6/19

Y1 - 2025/6/19

N2 - 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.

AB - 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.

KW - Forensic-Based Feature Selection

KW - Software-Defined Networking (SDN)

KW - Intrusion Detection System (IDS)

KW - Deep Learning

KW - Network Virtualization

UR - https://www.scopus.com/pages/publications/105009600446

UR - https://pure.ulster.ac.uk/en/publications/79ee5edc-0219-4f51-9856-4f3aded3c532

U2 - 10.1109/hpsr64165.2025.11038896

DO - 10.1109/hpsr64165.2025.11038896

M3 - Conference contribution

SN - 9798331529918

SN - 979-8-3315-2992-5

T3 - IEEE International Conference on High Performance Switching and Routing, HPSR

SP - 1

EP - 6

BT - 2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025

PB - IEEE

T2 - 2025 IEEE 26th International Conference on High Performance Switching and Routing (HPSR)

Y2 - 20 May 2025 through 22 May 2025

ER -

Gaurav A, Gupta BB, Chaurasia P, Arya V, Attar RW, Chui KT. AI-Powered Intrusion Detection for Secure and Efficient SDN in Network Virtualization. In 2025 IEEE 26th International Conference on High Performance Switching and Routing, HPSR 2025. IEEE. 2025. p. 1-6. (IEEE International Conference on High Performance Switching and Routing, HPSR). Epub 2025 Jun 19. doi: 10.1109/hpsr64165.2025.11038896

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

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this