Data-driven network intrusion detection using optimized machine learning algorithms
Network intrusion detection systems (NIDS) play a crucial role in maintaining cybersecurity by identifying malicious network activities. This study presents a comprehensive evaluation of machine learning approaches for network intrusion detection, comparing the performance of Decision Trees (DT), Ra...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Franklin Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2773186325001276 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226849170751488 |
|---|---|
| author | Dauda Adeite Adenusi Oladosu Oyebisi Oladimeji Theopilus Adekunle Oyekola Korede Solomon Olagunju |
| author_facet | Dauda Adeite Adenusi Oladosu Oyebisi Oladimeji Theopilus Adekunle Oyekola Korede Solomon Olagunju |
| author_sort | Dauda Adeite Adenusi |
| collection | DOAJ |
| description | Network intrusion detection systems (NIDS) play a crucial role in maintaining cybersecurity by identifying malicious network activities. This study presents a comprehensive evaluation of machine learning approaches for network intrusion detection, comparing the performance of Decision Trees (DT), Random Forest (RF), K-Nearest Neighbors (K-NN), Gradient Boosting (GB), and Logistic Regression (LR) algorithms. The research investigates the impact of data preprocessing techniques, including data balancing and duplicate removal, on detection performance. Experimental results demonstrate exceptional performance of tree-based methods, with DT and RF achieving accuracy rates of 0.9997 and 0.9996 respectively, alongside precision rates exceeding 0.99. Comparative analysis with existing approaches, including deep learning methods, shows that our optimized tree-based models achieve comparable or superior performance while maintaining computational efficiency. The proposed approach demonstrates perfect Area Under the Curve (AUC) scores of 1.00 for tree-based methods, indicating robust detection capabilities across varying decision thresholds. This research contributes to the field by establishing that simpler machine learning models can achieve state-of-the-art performance in network intrusion detection, offering practical implications for real-world deployment in network security operations. |
| format | Article |
| id | doaj-art-2b36dcddffc84a37bc6f99aae1fb905a |
| institution | Kabale University |
| issn | 2773-1863 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Franklin Open |
| spelling | doaj-art-2b36dcddffc84a37bc6f99aae1fb905a2025-08-24T05:15:35ZengElsevierFranklin Open2773-18632025-09-011210033910.1016/j.fraope.2025.100339Data-driven network intrusion detection using optimized machine learning algorithmsDauda Adeite Adenusi0Oladosu Oyebisi Oladimeji1Theopilus Adekunle Oyekola2Korede Solomon Olagunju3Department of Mathematical and Computing Sciences, KolaDaisi University, Ibadan, NigeriaFaculty of Engineering and Design, Atlantic Technological University, Sligo F91 YW50, Ireland; Corresponding author at: Faculty of Engineering and Design, Department of Computing and Electronics, Atlantic Technological University, F91 YW50 Sligo, Ireland.Department of Mathematical and Computing Sciences, KolaDaisi University, Ibadan, NigeriaDepartment of Mathematical and Computing Sciences, KolaDaisi University, Ibadan, NigeriaNetwork intrusion detection systems (NIDS) play a crucial role in maintaining cybersecurity by identifying malicious network activities. This study presents a comprehensive evaluation of machine learning approaches for network intrusion detection, comparing the performance of Decision Trees (DT), Random Forest (RF), K-Nearest Neighbors (K-NN), Gradient Boosting (GB), and Logistic Regression (LR) algorithms. The research investigates the impact of data preprocessing techniques, including data balancing and duplicate removal, on detection performance. Experimental results demonstrate exceptional performance of tree-based methods, with DT and RF achieving accuracy rates of 0.9997 and 0.9996 respectively, alongside precision rates exceeding 0.99. Comparative analysis with existing approaches, including deep learning methods, shows that our optimized tree-based models achieve comparable or superior performance while maintaining computational efficiency. The proposed approach demonstrates perfect Area Under the Curve (AUC) scores of 1.00 for tree-based methods, indicating robust detection capabilities across varying decision thresholds. This research contributes to the field by establishing that simpler machine learning models can achieve state-of-the-art performance in network intrusion detection, offering practical implications for real-world deployment in network security operations.http://www.sciencedirect.com/science/article/pii/S2773186325001276Intrusion detection systemMachine learningCyber securityData preprocessing |
| spellingShingle | Dauda Adeite Adenusi Oladosu Oyebisi Oladimeji Theopilus Adekunle Oyekola Korede Solomon Olagunju Data-driven network intrusion detection using optimized machine learning algorithms Franklin Open Intrusion detection system Machine learning Cyber security Data preprocessing |
| title | Data-driven network intrusion detection using optimized machine learning algorithms |
| title_full | Data-driven network intrusion detection using optimized machine learning algorithms |
| title_fullStr | Data-driven network intrusion detection using optimized machine learning algorithms |
| title_full_unstemmed | Data-driven network intrusion detection using optimized machine learning algorithms |
| title_short | Data-driven network intrusion detection using optimized machine learning algorithms |
| title_sort | data driven network intrusion detection using optimized machine learning algorithms |
| topic | Intrusion detection system Machine learning Cyber security Data preprocessing |
| url | http://www.sciencedirect.com/science/article/pii/S2773186325001276 |
| work_keys_str_mv | AT daudaadeiteadenusi datadrivennetworkintrusiondetectionusingoptimizedmachinelearningalgorithms AT oladosuoyebisioladimeji datadrivennetworkintrusiondetectionusingoptimizedmachinelearningalgorithms AT theopilusadekunleoyekola datadrivennetworkintrusiondetectionusingoptimizedmachinelearningalgorithms AT koredesolomonolagunju datadrivennetworkintrusiondetectionusingoptimizedmachinelearningalgorithms |