A stacked ensemble approach to detect cyber attacks based on feature selection techniques
The exponential growth of data and increased reliance on interconnected systems have heightened the need for robust network security. Cyber-Attack Detection Systems (CADS) are essential for identifying and mitigating threats through network traffic analysis. However, the effectiveness of CADS is hig...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2024-01-01
|
| Series: | International Journal of Cognitive Computing in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666307424000263 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850198268784410624 |
|---|---|
| author | Wahida Ferdose Urmi Mohammed Nasir Uddin Md Ashraf Uddin Md. Alamin Talukder Md. Rahat Hasan Souvik Paul Moumita Chanda John Ayoade Ansam Khraisat Rakib Hossen Faisal Imran |
| author_facet | Wahida Ferdose Urmi Mohammed Nasir Uddin Md Ashraf Uddin Md. Alamin Talukder Md. Rahat Hasan Souvik Paul Moumita Chanda John Ayoade Ansam Khraisat Rakib Hossen Faisal Imran |
| author_sort | Wahida Ferdose Urmi |
| collection | DOAJ |
| description | The exponential growth of data and increased reliance on interconnected systems have heightened the need for robust network security. Cyber-Attack Detection Systems (CADS) are essential for identifying and mitigating threats through network traffic analysis. However, the effectiveness of CADS is highly dependent on selecting pertinent features. This research evaluates the impact of three feature selection techniques—Recursive Feature Elimination (RFE), Mutual Information (MI), and Lasso Feature Selection (LFS)—on CADS performance. We propose a novel stacked ensemble classification approach, combining Random Forest, XGBoost, and Extra-Trees classifiers with a Logistic Regression meta-model. Performance is assessed using CICIDS2017 and NSL-KDD datasets. Results show that RFE achieves 100% accuracy for Brute Force attacks, 99.99% for Infiltration and Web Attacks on CICIDS2017, and 99.95% accuracy for all attacks on NSL-KDD, marking a significant improvement over traditional methods. This study demonstrates that optimizing feature selection and leveraging diverse classifiers can substantially enhance the accuracy of CADS, providing stronger protection against evolving cyber threats. |
| format | Article |
| id | doaj-art-dcde3e5bbd6b4b9cb2a40a55824dbdfd |
| institution | OA Journals |
| issn | 2666-3074 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | International Journal of Cognitive Computing in Engineering |
| spelling | doaj-art-dcde3e5bbd6b4b9cb2a40a55824dbdfd2025-08-20T02:12:54ZengKeAi Communications Co., Ltd.International Journal of Cognitive Computing in Engineering2666-30742024-01-01531633110.1016/j.ijcce.2024.07.005A stacked ensemble approach to detect cyber attacks based on feature selection techniquesWahida Ferdose Urmi0Mohammed Nasir Uddin1Md Ashraf Uddin2Md. Alamin Talukder3Md. Rahat Hasan4Souvik Paul5Moumita Chanda6John Ayoade7Ansam Khraisat8Rakib Hossen9Faisal Imran10Department of Computer Science and Engineering, Jagannath University, Dhaka, BangladeshDepartment of Computer Science and Engineering, Jagannath University, Dhaka, BangladeshSchool of Information Technology, Deakin University, Waurn Ponds Campus, Geelong, Australia; School of Information Technology, Crown Institute of Higher Education, 116 Pacific Highway, North Sydney, NSW, 2060, Australia; Corresponding author at: School of Information Technology, Deakin University, Waurn Ponds Campus, Geelong, Australia.Department of Computer Science and Engineering, International University of Business Agriculture and Technology, Dhaka, Bangladesh; Corresponding author.Department of Computer Science and Engineering, Jagannath University, Dhaka, BangladeshDepartment of Electrical and Computer Engineering, University of Ottawa, CanadaDepartment of Computer Science and Engineering, International University of Business Agriculture and Technology, Dhaka, BangladeshSchool of Information Technology, Crown Institute of Higher Education, 116 Pacific Highway, North Sydney, NSW, 2060, AustraliaSchool of Information Technology, Deakin University, Waurn Ponds Campus, Geelong, AustraliaDepartment of Cyber Security, Bangabandhu Sheikh Mujibur Rahman Digital University, Kaliakoir, Gazipur, 1750, BangladeshDepartment of Computer Science and Engineering, International University of Business Agriculture and Technology, Dhaka, BangladeshThe exponential growth of data and increased reliance on interconnected systems have heightened the need for robust network security. Cyber-Attack Detection Systems (CADS) are essential for identifying and mitigating threats through network traffic analysis. However, the effectiveness of CADS is highly dependent on selecting pertinent features. This research evaluates the impact of three feature selection techniques—Recursive Feature Elimination (RFE), Mutual Information (MI), and Lasso Feature Selection (LFS)—on CADS performance. We propose a novel stacked ensemble classification approach, combining Random Forest, XGBoost, and Extra-Trees classifiers with a Logistic Regression meta-model. Performance is assessed using CICIDS2017 and NSL-KDD datasets. Results show that RFE achieves 100% accuracy for Brute Force attacks, 99.99% for Infiltration and Web Attacks on CICIDS2017, and 99.95% accuracy for all attacks on NSL-KDD, marking a significant improvement over traditional methods. This study demonstrates that optimizing feature selection and leveraging diverse classifiers can substantially enhance the accuracy of CADS, providing stronger protection against evolving cyber threats.http://www.sciencedirect.com/science/article/pii/S2666307424000263Network-based intrusion detection systemHost-based intrusion detection systemWeb attacksStack ensemble modelBinary classificationMulticlass classification |
| spellingShingle | Wahida Ferdose Urmi Mohammed Nasir Uddin Md Ashraf Uddin Md. Alamin Talukder Md. Rahat Hasan Souvik Paul Moumita Chanda John Ayoade Ansam Khraisat Rakib Hossen Faisal Imran A stacked ensemble approach to detect cyber attacks based on feature selection techniques International Journal of Cognitive Computing in Engineering Network-based intrusion detection system Host-based intrusion detection system Web attacks Stack ensemble model Binary classification Multiclass classification |
| title | A stacked ensemble approach to detect cyber attacks based on feature selection techniques |
| title_full | A stacked ensemble approach to detect cyber attacks based on feature selection techniques |
| title_fullStr | A stacked ensemble approach to detect cyber attacks based on feature selection techniques |
| title_full_unstemmed | A stacked ensemble approach to detect cyber attacks based on feature selection techniques |
| title_short | A stacked ensemble approach to detect cyber attacks based on feature selection techniques |
| title_sort | stacked ensemble approach to detect cyber attacks based on feature selection techniques |
| topic | Network-based intrusion detection system Host-based intrusion detection system Web attacks Stack ensemble model Binary classification Multiclass classification |
| url | http://www.sciencedirect.com/science/article/pii/S2666307424000263 |
| work_keys_str_mv | AT wahidaferdoseurmi astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mohammednasiruddin astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mdashrafuddin astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mdalamintalukder astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mdrahathasan astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT souvikpaul astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT moumitachanda astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT johnayoade astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT ansamkhraisat astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT rakibhossen astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT faisalimran astackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT wahidaferdoseurmi stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mohammednasiruddin stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mdashrafuddin stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mdalamintalukder stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT mdrahathasan stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT souvikpaul stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT moumitachanda stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT johnayoade stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT ansamkhraisat stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT rakibhossen stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques AT faisalimran stackedensembleapproachtodetectcyberattacksbasedonfeatureselectiontechniques |