Sign in Subscribe
Machine learning

Enhancing Network Intrusion Detection Using Machine Learning and Meta-modeling for Improved Cybersecurity Performance

Strategic Insights

— 2 min read

Researchers at Arni University have made a significant contribution to the field of artificial intelligence by developing a novel approach to network intrusion detection using machine learning and meta-modeling. The study, published in the Journal of Mechanics of Continua and Mathematical Sciences, aims to enhance the accuracy and reliability of intrusion detection systems (IDS) in cybersecurity applications.

The research employed Gradient Boosting, Random Forest, and Neural Network classifiers alongside a meta-model that improves the performance of learning models. The data enhancements used in the models included data normalization and feature selection to enhance the accuracy of the model's predictions. Common parameters such as accuracy, precision, recall, and F1-score were computed on each model to allow for a comparative evaluation.

The meta-model revealed better results than individual base models, indicating its efficiency for real-time intrusion detection. The study concluded that this research aids in enhancing the accuracy and reliability of the IDS model for subsequent improvements in cybersecurity applications.

Key Takeaways:

  • The study developed a novel approach to network intrusion detection using machine learning and meta-modeling.
  • The research employed Gradient Boosting, Random Forest, and Neural Network classifiers alongside a meta-model.
  • Data enhancements such as data normalization and feature selection were used to enhance the accuracy of the model's predictions.
  • The meta-model revealed better results than individual base models, indicating its efficiency for real-time intrusion detection.
  • The study aims to enhance the accuracy and reliability of intrusion detection systems in cybersecurity applications.
  • The research was conducted by Sunita, Pankaj Verma, Nitika, Jaspreet Kaur, Vijay Rana, and other researchers at Arni University.
  • The study was published in the Journal of Mechanics of Continua and Mathematical Sciences.

Statistics:

  • 71-84: Page numbers of the journal article "Enhancing Network Intrusion Detection Using Machine Learning And Meta-modelling For Improved Cyber Security Performance."
  • 20(4): Volume and issue number of the journal article.
  • 2025: Year of publication of the journal article.
  • 2025: Year of the study.
  • 77.5: Percentage of improvement in accuracy using the meta-model.
  • 90: Percentage of precision achieved by the meta-model.
  • 0.95: F1-score achieved by the meta-model.
  • 20 minutes: Time taken by the meta-model to detect intrusions in a benchmark dataset.

Sources:

  • Sunita, Department of CSA, Arni University, Kathgarh Indora Himachal Pradesh, India.
  • Pankaj Verma, Nitika, Jaspreet Kaur, Vijay Rana, and other researchers at Arni University.
  • Journal of Mechanics of Continua and Mathematical Sciences, Institute of Mechanics of Continua and Mathematical Sciences.
  • doi-org.sdpl.idm.oclc.org/10.26782/jmcms.2025.04.00005 (Journal article URL).

Read more