Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble Techniques
The deployment of intrusion detection systems (IDSs) is essential for protecting network resources and infrastructure against malicious threats. Despite the wide use of various machine learning methods in IDSs, such systems often struggle to achieve optimal performance. The key challenges include th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/17/12/550 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850036445909090304 |
|---|---|
| author | Ali Mohammed Alsaffar Mostafa Nouri-Baygi Hamed Zolbanin |
| author_facet | Ali Mohammed Alsaffar Mostafa Nouri-Baygi Hamed Zolbanin |
| author_sort | Ali Mohammed Alsaffar |
| collection | DOAJ |
| description | The deployment of intrusion detection systems (IDSs) is essential for protecting network resources and infrastructure against malicious threats. Despite the wide use of various machine learning methods in IDSs, such systems often struggle to achieve optimal performance. The key challenges include the curse of dimensionality, which significantly impacts IDS efficacy, and the limited effectiveness of singular learning classifiers in handling complex, imbalanced, and multi-categorical traffic datasets. To overcome these limitations, this paper presents an innovative approach that integrates dimensionality reduction and stacking ensemble techniques. We employ the LogitBoost algorithm with XGBRegressor for feature selection, complemented by a Residual Network (ResNet) deep learning model for feature extraction. Furthermore, we introduce multi-stacking ensemble (MSE), a novel ensemble method, to enhance attack prediction capabilities. The evaluation on benchmark datasets such as CICIDS2017 and UNSW-NB15 demonstrates that our IDS surpasses current models across various performance metrics. |
| format | Article |
| id | doaj-art-3f3e134720e84ce8a09a7c416da52990 |
| institution | DOAJ |
| issn | 1999-4893 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-3f3e134720e84ce8a09a7c416da529902025-08-20T02:57:08ZengMDPI AGAlgorithms1999-48932024-12-01171255010.3390/a17120550Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble TechniquesAli Mohammed Alsaffar0Mostafa Nouri-Baygi1Hamed Zolbanin2Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad 9177948944, IranDepartment of Computer Engineering, Ferdowsi University of Mashhad, Mashhad 9177948944, IranSchool of Business Administration, University of Dayton, Dayton, OH 45469, USAThe deployment of intrusion detection systems (IDSs) is essential for protecting network resources and infrastructure against malicious threats. Despite the wide use of various machine learning methods in IDSs, such systems often struggle to achieve optimal performance. The key challenges include the curse of dimensionality, which significantly impacts IDS efficacy, and the limited effectiveness of singular learning classifiers in handling complex, imbalanced, and multi-categorical traffic datasets. To overcome these limitations, this paper presents an innovative approach that integrates dimensionality reduction and stacking ensemble techniques. We employ the LogitBoost algorithm with XGBRegressor for feature selection, complemented by a Residual Network (ResNet) deep learning model for feature extraction. Furthermore, we introduce multi-stacking ensemble (MSE), a novel ensemble method, to enhance attack prediction capabilities. The evaluation on benchmark datasets such as CICIDS2017 and UNSW-NB15 demonstrates that our IDS surpasses current models across various performance metrics.https://www.mdpi.com/1999-4893/17/12/550intrusion detection systemLogitBoostResNetmachine learningstacking ensemble |
| spellingShingle | Ali Mohammed Alsaffar Mostafa Nouri-Baygi Hamed Zolbanin Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble Techniques Algorithms intrusion detection system LogitBoost ResNet machine learning stacking ensemble |
| title | Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble Techniques |
| title_full | Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble Techniques |
| title_fullStr | Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble Techniques |
| title_full_unstemmed | Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble Techniques |
| title_short | Enhancing Intrusion Detection Systems with Dimensionality Reduction and Multi-Stacking Ensemble Techniques |
| title_sort | enhancing intrusion detection systems with dimensionality reduction and multi stacking ensemble techniques |
| topic | intrusion detection system LogitBoost ResNet machine learning stacking ensemble |
| url | https://www.mdpi.com/1999-4893/17/12/550 |
| work_keys_str_mv | AT alimohammedalsaffar enhancingintrusiondetectionsystemswithdimensionalityreductionandmultistackingensembletechniques AT mostafanouribaygi enhancingintrusiondetectionsystemswithdimensionalityreductionandmultistackingensembletechniques AT hamedzolbanin enhancingintrusiondetectionsystemswithdimensionalityreductionandmultistackingensembletechniques |