IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection Method
The Internet of Things (IoT) ecosystem has experienced significant growth in data traffic and consequently high dimensionality. Intrusion Detection Systems (IDSs) are essential self-protective tools against various cyber-attacks. However, IoT IDS systems face significant challenges due to functional...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/10/5015 |
| _version_ | 1797501781424472064 |
|---|---|
| author | Khalid Albulayhi Qasem Abu Al-Haija Suliman A. Alsuhibany Ananth A. Jillepalli Mohammad Ashrafuzzaman Frederick T. Sheldon |
| author_facet | Khalid Albulayhi Qasem Abu Al-Haija Suliman A. Alsuhibany Ananth A. Jillepalli Mohammad Ashrafuzzaman Frederick T. Sheldon |
| author_sort | Khalid Albulayhi |
| collection | DOAJ |
| description | The Internet of Things (IoT) ecosystem has experienced significant growth in data traffic and consequently high dimensionality. Intrusion Detection Systems (IDSs) are essential self-protective tools against various cyber-attacks. However, IoT IDS systems face significant challenges due to functional and physical diversity. These IoT characteristics make exploiting all features and attributes for IDS self-protection difficult and unrealistic. This paper proposes and implements a novel feature selection and extraction approach (i.e., our method) for anomaly-based IDS. The approach begins with using two entropy-based approaches (i.e., information gain (IG) and gain ratio (GR)) to select and extract relevant features in various ratios. Then, mathematical set theory (union and intersection) is used to extract the best features. The model framework is trained and tested on the IoT intrusion dataset 2020 (IoTID20) and NSL-KDD dataset using four machine learning algorithms: Bagging, Multilayer Perception, J48, and IBk. Our approach has resulted in 11 and 28 relevant features (out of 86) using the intersection and union, respectively, on IoTID20 and resulted 15 and 25 relevant features (out of 41) using the intersection and union, respectively, on NSL-KDD. We have further compared our approach with other state-of-the-art studies. The comparison reveals that our model is superior and competent, scoring a very high 99.98% classification accuracy. |
| first_indexed | 2024-03-10T03:24:30Z |
| format | Article |
| id | doaj.art-81c3bc57751b45c8b808807eb25eb1e4 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:24:30Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-81c3bc57751b45c8b808807eb25eb1e42023-11-23T09:56:29ZengMDPI AGApplied Sciences2076-34172022-05-011210501510.3390/app12105015IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection MethodKhalid Albulayhi0Qasem Abu Al-Haija1Suliman A. Alsuhibany2Ananth A. Jillepalli3Mohammad Ashrafuzzaman4Frederick T. Sheldon5Computer Science Department, University of Idaho, Moscow, ID 83844, USADepartment of Computer Science/Cybersecurity, Princess Sumaya University for Technology (PSUT), Amman 11941, JordanDepartment of Computer Science, College of Computer, Qassim University, Buraydah 51452, Saudi ArabiaSchool of Electrical Engineering and Computer Science, Washington State University, Pullman, WA 99164, USADepartment of Mathematics and Computer Science, Ashland University, Ashland, OH 44805, USAComputer Science Department, University of Idaho, Moscow, ID 83844, USAThe Internet of Things (IoT) ecosystem has experienced significant growth in data traffic and consequently high dimensionality. Intrusion Detection Systems (IDSs) are essential self-protective tools against various cyber-attacks. However, IoT IDS systems face significant challenges due to functional and physical diversity. These IoT characteristics make exploiting all features and attributes for IDS self-protection difficult and unrealistic. This paper proposes and implements a novel feature selection and extraction approach (i.e., our method) for anomaly-based IDS. The approach begins with using two entropy-based approaches (i.e., information gain (IG) and gain ratio (GR)) to select and extract relevant features in various ratios. Then, mathematical set theory (union and intersection) is used to extract the best features. The model framework is trained and tested on the IoT intrusion dataset 2020 (IoTID20) and NSL-KDD dataset using four machine learning algorithms: Bagging, Multilayer Perception, J48, and IBk. Our approach has resulted in 11 and 28 relevant features (out of 86) using the intersection and union, respectively, on IoTID20 and resulted 15 and 25 relevant features (out of 41) using the intersection and union, respectively, on NSL-KDD. We have further compared our approach with other state-of-the-art studies. The comparison reveals that our model is superior and competent, scoring a very high 99.98% classification accuracy.https://www.mdpi.com/2076-3417/12/10/5015cybersecurityanomaly detection accuracyfeature selectionInternet of Things (IoT)intrusion detection systemand machine learning |
| spellingShingle | Khalid Albulayhi Qasem Abu Al-Haija Suliman A. Alsuhibany Ananth A. Jillepalli Mohammad Ashrafuzzaman Frederick T. Sheldon IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection Method Applied Sciences cybersecurity anomaly detection accuracy feature selection Internet of Things (IoT) intrusion detection system and machine learning |
| title | IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection Method |
| title_full | IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection Method |
| title_fullStr | IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection Method |
| title_full_unstemmed | IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection Method |
| title_short | IoT Intrusion Detection Using Machine Learning with a Novel High Performing Feature Selection Method |
| title_sort | iot intrusion detection using machine learning with a novel high performing feature selection method |
| topic | cybersecurity anomaly detection accuracy feature selection Internet of Things (IoT) intrusion detection system and machine learning |
| url | https://www.mdpi.com/2076-3417/12/10/5015 |
| work_keys_str_mv | AT khalidalbulayhi iotintrusiondetectionusingmachinelearningwithanovelhighperformingfeatureselectionmethod AT qasemabualhaija iotintrusiondetectionusingmachinelearningwithanovelhighperformingfeatureselectionmethod AT sulimanaalsuhibany iotintrusiondetectionusingmachinelearningwithanovelhighperformingfeatureselectionmethod AT ananthajillepalli iotintrusiondetectionusingmachinelearningwithanovelhighperformingfeatureselectionmethod AT mohammadashrafuzzaman iotintrusiondetectionusingmachinelearningwithanovelhighperformingfeatureselectionmethod AT fredericktsheldon iotintrusiondetectionusingmachinelearningwithanovelhighperformingfeatureselectionmethod |