Email Alert-Enabled Network Intrusion Detection Systems: A Supervised Machine Learning Approach with Recursive Feature Elimination

@article{1705375,
      author = {Mohammad Aman, Ashishika Singh, Tushar J Malviya, Aditi A Kalgi, Shreya Hegde; Harsh Kumar},
      title = {Email Alert-Enabled Network Intrusion Detection Systems: A Supervised Machine Learning Approach with Recursive Feature Elimination},
      journal = {Iconic Research And Engineering Journals},
      year = {2024},
      volume = {7},
      number = {7},
      pages = {110-118},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1705375.pdf},
      abstract = {In the evolving cybersecurity environment, the importance of a robust intrusion detection system (IDS) is paramount. This research explores the integration of supervised machine learning models such as decision trees, support vector machines (SVMs) and random forests to improve the capabilities of network intrusion detection systems (NIDS). The proposed methodology includes data pre-processing, feature selection and model training using the KDD-Cup99 dataset. This research presents a comparative analysis of the performance of a model with 41 features and a reduced set of 15 features obtained by recursive feature elimination (RFE). This research contributes to understanding the effectiveness of machine learning in strengthening email-alert enabled NIDS against cyber threats.},
      keywords = {Network intrusion, Supervised Machine learning, Network Attack detection, Network Security, Email-Alert, Threat Detection.},
      month = {January},
  }