T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection Systems
Abstract In the last few decades, Intrusion Detection System (IDS), in particular, machine learning‐based anomaly detection, has gained importance over Signature Detection Systems (SDSs) in the novel attacks detection. Herein, a novel approach called T‐Distributed Stochastic Neighbour Embedding and...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-IET
2021-03-01
|
| Series: | IET Information Security |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ise2.12020 |
| _version_ | 1797423197714382848 |
|---|---|
| author | Mohamed Hammad Nabil Hewahi Wael Elmedany |
| author_facet | Mohamed Hammad Nabil Hewahi Wael Elmedany |
| author_sort | Mohamed Hammad |
| collection | DOAJ |
| description | Abstract In the last few decades, Intrusion Detection System (IDS), in particular, machine learning‐based anomaly detection, has gained importance over Signature Detection Systems (SDSs) in the novel attacks detection. Herein, a novel approach called T‐Distributed Stochastic Neighbour Embedding and Random Forest Algorithm (T‐SNERF) is presented for the classification of cyber‐attacks. The approach consists of three different steps. First, the examination of feature correlations is provided. Second, the T‐Distributed Stochastic Neighbour Embedding (T‐SNE) data dimensional reduction technique is used. Third, Random Forest (RF) technique is utilised to evaluate the complications in the accuracy and False‐Positive Rate (FPR). The proposed approach has been tested on various well‐known datasets, namely, UNSW‐NB 15, CICIDS‐2017, and phishing datasets. The proposed novel approach achieved significant results compared with existing approaches, achieving 100% accuracy, and 0% FPR for the UNSW‐NB15 dataset, and achieving high accuracy rates, up to 99.7878%, and 99.7044%, for CICIDS‐2017 and Phishing datasets respectively. |
| first_indexed | 2024-03-09T07:42:57Z |
| format | Article |
| id | doaj.art-208eed3588bc486e8348621cd3cd1c11 |
| institution | Directory Open Access Journal |
| issn | 1751-8709 1751-8717 |
| language | English |
| last_indexed | 2024-03-09T07:42:57Z |
| publishDate | 2021-03-01 |
| publisher | Hindawi-IET |
| record_format | Article |
| series | IET Information Security |
| spelling | doaj.art-208eed3588bc486e8348621cd3cd1c112023-12-03T04:16:23ZengHindawi-IETIET Information Security1751-87091751-87172021-03-0115217819010.1049/ise2.12020T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection SystemsMohamed Hammad0Nabil Hewahi1Wael Elmedany2College of Information Technology University of Bahrain Sakhir Manama BahrainCollege of Information Technology University of Bahrain Sakhir Manama BahrainCollege of Information Technology University of Bahrain Sakhir Manama BahrainAbstract In the last few decades, Intrusion Detection System (IDS), in particular, machine learning‐based anomaly detection, has gained importance over Signature Detection Systems (SDSs) in the novel attacks detection. Herein, a novel approach called T‐Distributed Stochastic Neighbour Embedding and Random Forest Algorithm (T‐SNERF) is presented for the classification of cyber‐attacks. The approach consists of three different steps. First, the examination of feature correlations is provided. Second, the T‐Distributed Stochastic Neighbour Embedding (T‐SNE) data dimensional reduction technique is used. Third, Random Forest (RF) technique is utilised to evaluate the complications in the accuracy and False‐Positive Rate (FPR). The proposed approach has been tested on various well‐known datasets, namely, UNSW‐NB 15, CICIDS‐2017, and phishing datasets. The proposed novel approach achieved significant results compared with existing approaches, achieving 100% accuracy, and 0% FPR for the UNSW‐NB15 dataset, and achieving high accuracy rates, up to 99.7878%, and 99.7044%, for CICIDS‐2017 and Phishing datasets respectively.https://doi.org/10.1049/ise2.12020computer crimefeature extractionlearning (artificial intelligence)pattern classificationrandom forests |
| spellingShingle | Mohamed Hammad Nabil Hewahi Wael Elmedany T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection Systems IET Information Security computer crime feature extraction learning (artificial intelligence) pattern classification random forests |
| title | T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection Systems |
| title_full | T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection Systems |
| title_fullStr | T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection Systems |
| title_full_unstemmed | T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection Systems |
| title_short | T‐SNERF: A novel high accuracy machine learning approach for Intrusion Detection Systems |
| title_sort | t snerf a novel high accuracy machine learning approach for intrusion detection systems |
| topic | computer crime feature extraction learning (artificial intelligence) pattern classification random forests |
| url | https://doi.org/10.1049/ise2.12020 |
| work_keys_str_mv | AT mohamedhammad tsnerfanovelhighaccuracymachinelearningapproachforintrusiondetectionsystems AT nabilhewahi tsnerfanovelhighaccuracymachinelearningapproachforintrusiondetectionsystems AT waelelmedany tsnerfanovelhighaccuracymachinelearningapproachforintrusiondetectionsystems |