Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

An efficient and interpretable intrusion detection framework for software-defined networks with multi-class

Md Tamim Hasan Saykat1, Md Ehsanul Haque2, Fahmid Al Farid3,4

  • 1Department of Computer Science and Engineering, East West University, Dhaka, 1212, Bangladesh.

Scientific Reports
|July 9, 2026
PubMed
Summary

Related Concept Videos

Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cross-domain intelligent fault diagnosis with superlet spectrograms and a parameter-efficient CNN-Transformer hybrid.

Scientific reports·2026
Same author

Hilbert-domain sub-band feature framework for EEG-based seizure detection.

Frontiers in computational neuroscience·2026
Same author

Electrochemical CO<sub>2</sub> capture from engine exhaust using NaCl electrolyte: System modeling, optimization, and economic assessment.

Scientific reports·2026
Same author

When uncertainty guides learning: a highly effective approach to kidney disease classification in CT imaging.

Frontiers in big data·2026
Same author

Privacy-aware diabetic retinopathy grading and visual lesion-focused interpretability through mixture-of-experts federated deep learning with explainable AI.

Scientific reports·2026
Same author

KDH-Net: Explainable Medical AI for Multiclass Kidney Disease Characterization from CT Images.

Journal of clinical medicine·2026

This study introduces a hybrid intrusion detection system (IDS) for Software-Defined Networks (SDNs) using Generative Adversarial Networks (GANs) and Explainable AI (XAI). The OptiXGB-IDS framework enhances cybersecurity by accurately detecting complex threats in SDN environments.

Area of Science:

  • Cybersecurity
  • Network Security
  • Artificial Intelligence in Cybersecurity

Background:

  • Software-Defined Networks (SDNs) face significant cybersecurity challenges due to inherent weaknesses, exacerbated by the projected growth of Internet of Things (IoT) devices.
  • Conventional Intrusion Detection Systems (IDS) struggle with imbalanced data, high-dimensional features, and a lack of interpretability in SDN environments.
  • The expanding threat surface in the IoT era necessitates advanced, robust, and interpretable cybersecurity solutions for SDNs.

Purpose of the Study:

  • To propose a hybrid SDN-based IDS framework integrating Generative Adversarial Networks (GANs) and Explainable AI (XAI) techniques.
  • To address challenges of imbalanced datasets, feature selection, and classifier optimization for enhanced intrusion detection.
  • To achieve robust, accurate, and interpretable cyber threat detection in SDN-based IoT environments.

Related Experiment Videos

Main Methods:

  • Integration of Generative Adversarial Networks (GANs) for handling imbalanced datasets.
  • Application of one-way ANOVA and Genetic Algorithm (GA) for effective feature selection.
  • Optimization of classifiers using Grid Search and implementation of Explainable AI (XAI) techniques (SHAP, LIME, Morris analysis) for interpretability.

Main Results:

  • The optimized XGBoost model (OptiXGB-IDS) achieved 99.87% accuracy on the InSDN dataset with high precision, recall, and F1-scores.
  • Cross-dataset validation on CIC-IDS2017 showed OptiXGB-IDS achieving 98.70% accuracy, outperforming competing models.
  • The framework demonstrated significant improvements in IDS performance, spatial and temporal feature learning, and robustness.

Conclusions:

  • The proposed hybrid GA-GAN-XAI framework offers a precise and reliable solution for detecting complex and novel cyber threats in SDN environments.
  • The integration of GANs, GA, and XAI significantly enhances IDS capabilities, addressing key limitations of conventional systems.
  • The developed framework provides a robust defense mechanism against evolving cyber-attacks in the context of SDN and IoT.